Saturday, July 2, 2011
Call for papers: WSDM 2012
The deadline for submitting abstracts to the Fifth ACM International Conference on Web Search and Data Mining (WSDM) 2012 is 4 August 2011, while the deadline for submitting full papers is 11 August 2011. This conference will be held in Seattle, Washington, February 8-12 2012.
Call for papers: SIAM SDM 12
The deadline for submitting papers to the SIAM International Conference on Data Mining (SDM) 2012 is 14 October 2011. This conference will be held in Anaheim, California, April 26-28, 2012.
Friday, July 1, 2011
Call for papers: ISNN 2012
The deadline for submitting papers to the 2012 International Symposium on Neural Networks (ISNN 2012) is 15 January 2012. This symposium will be held in Shenyang, China, July 11-14, 2012.
I visited Shenyang in 2005 and found it to be energetic but also very friendly. Shenyang is easily my favourite city in China and I look forward to visiting again.
I visited Shenyang in 2005 and found it to be energetic but also very friendly. Shenyang is easily my favourite city in China and I look forward to visiting again.
Wednesday, June 29, 2011
Teaching Materials Online
I have just made lecture materials from my undergraduate computational intelligence course available online. The lectures cover rule-based systems, fuzzy logic, artificial neural networks, evolutionary algorithms and hybrid systems. The lectures are available at: http://mike.watts.net.nz/Teaching/
These lectures were presented in the course INFO 331, Intelligent Information Systems, during my time at the Department of Information Science at the University of Otago, New Zealand. Also available at the above address are lectures I presented for the course INFO 233, Data Processing.
These lectures were presented in the course INFO 331, Intelligent Information Systems, during my time at the Department of Information Science at the University of Otago, New Zealand. Also available at the above address are lectures I presented for the course INFO 233, Data Processing.
Tuesday, June 28, 2011
Deadline extended: AI 2011
The deadline for papers submitted to the 24th Australasian Joint Conference on Artificial Intelligence (AI 2011) has been extended from 28 June 2011 to 15 July 2011. This conference will be held in Perth, Western Australia, 5th to 8th December, 2011.
Saturday, June 25, 2011
Call for papers: ICIST 2012
The deadline for submitting papers to the International Conference on Intelligent Systems and Technologies (ICIST) 2012 is December 30, 2011. This conference will be held in Tokyo, Japan, 29-31 May 2012.
Friday, June 24, 2011
Paper deadline: EAIS 2012
The deadline for submitting papers to the IEEE Workshop on Evolving and Adaptive Intelligent Systems (EAIS) 2012 is 1 November 2011. This conference will be held in Madrid, Spain, 17-18 May, 2012.
Thursday, June 23, 2011
Call for papers: CINTI 2011
The deadline to submit papers to the 12th IEEE International Symposium on Computational Intelligence and Informatics (CINTI) 2011 is September 30 2011. This conference will be held in Budapest, Hungary, November 21-22 2011.
Tuesday, June 21, 2011
Call for papers: ICCIEA 2011
The deadline for papers submitted to the International Conference on Computational Intelligence and Engineering Applications (ICCIEA) 2011 is 1 September 2011. This conference will be held in Bhubaneswar, India, 16-17 October, 2011.
Call for papers: Collective Intelligence 2012
The deadline for papers submitted to the 2012 conference on Collective Intelligence is 4 November, 2011. This conference will be held in Cambridge, Massachusetts, April 18-20, 2012.
Monday, June 20, 2011
Conference paper deadline: MMIS 2011
The deadline for submitting papers to the 5th International Workshop on Mining Multiple Information Sources (MMIS-11) is July 23, 2011. This workshop will be held in Vancouver, Canada, December 10 2011.
Conference paper deadline: ICAISC 2012
The paper submission deadline for the 11th International Conference on Artificial Intelligence and Soft Computing (ICAISC) 2012 is 20 October, 2011. This conference will be held in Zakopane, Poland, April 29 - May 3, 2012.
Paper submission deadline: IEA AIE 2012
The paper submission deadline for the 25th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA AIE) 2012 is 11 November, 2011. This conference will be held in Dalian, China, June 9-12, 2012.
Sunday, June 19, 2011
Conference paper deadline: ICPRAM 2012
The deadline for submitting papers to the 1st International Conference on Pattern Recognition Applications and Methods (ICPRAM) 2012 is 26 July 2011. This conference will be held in Vilamoura, Portugal, 6-8 February 2011.
Paper submission deadline: PICom 2011
The deadline for papers submitted to the 9th International Conference on Pervasive Intelligence and Computing (PICOM) 2011 is July 15 2011. This conference will be held in Sydney, Australia, December 12-14 2011.
Paper submission deadline: PAKDD 2012
The deadline for submitting abstracts to the 16th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) 2012 is 25 September 2011. This conference will be held in Kuala Lumpur 29 May - 1 June, 2012.
Conference paper deadline: SAMI 2012
The paper submission deadline to the 10th IEEE International Symposium and Applied Machine Intelligence and Informatics (SAMI) 2012 is 31 October 2011. This symposium will be held January 26-28 2011 in Herl'any, Slovakia.
Saturday, June 18, 2011
Paper submission deadline: ICAART 2012
The deadline for papers submitted to the 4th International Conference on Agents and Artificial Intelligence (ICAART) 2012 is July 28, 2011. This conference will be held in Vilamoura, Portugal, 6-8 February, 2012.
Conference paper deadline: CIB 2011
The deadline for papers submitted to the 6th International Conference on Computational Intelligence and Bioinformatics (CIB) 2011 is 1st August, 2011. This conference will be held in Pittsburgh, USA, November 7-9, 2011.
Conference paper deadline: TAAI 2011
The deadline for papers submitted to the 2011 Conference on Technologies and Applications of Artificial Intelligence (TAAI) 2011 is July 12 2011. This conference will be held in Taoyuan, Taiwan, November 11-13 2011.
Friday, June 17, 2011
Conference paper deadline: ADMA 2011
The deadline for submitting papers to the 7th International Conference on Advanced Data Mining and Applications (ADMA) 2011 is July 7 2011. This conference will be held in Beijing, China, 17-19 December, 2011.
Call for papers: AISec 2011
The deadline for papers submitted to the 4th Workshop on Artificial Intelligence and Security (AISec) 2011 is July 6 2011. This conference will be held in Chicago, Illinois, 21 October 2011.
Paper submission deadline: MICAI 2011
The deadline for registration of abstracts for the 10th Mexican International Conference on Artificial Intelligence (MICAI) 2011 is July 1, 2011, with full papers due July 7, 2011. This conference will be held in Puebla, Mexico, November 26 - December 4, 2011.
Paper submission deadline: CiSE 2011
The deadline for papers submitted to the International Conference on Computational Intelligence and Software Engineering (CiSE) 2011 is July 20, 2011. This conference will be held in Wuhan, China, December 9-11, 2011.
Call for papers: CIS 2011
The deadline for papers submitted to the 7th International Conference on Computational Intelligence and Security (CIS) 2011 is 30 June 2011. This conference will be held in Sanya, Hainan, China, on December 3-4, 2011.
Thursday, June 16, 2011
Paper submission deadline: HIS 2011
The deadline for papers submitted to the 11th International Conference on Hybrid Intelligent Systems (HIS) 2011 is July 1, 2011. This conference will be held in Malacca, Malaysia, 5-8 December, 2011.
Paper submission deadline: IWACI 2011
The deadline for papers submitted to the Fourth International Workshop on Advanced Computational Intelligence (IWACI) 2011 is July 1, 2011. This conference will be held in Wuhan, China, October 19-21 2011.
Conference paper deadline: CIDM 2011
The deadline for papers submitted to the Second International Workshop on Computational Intelligence for Disaster Management (CIDM-2011) is 30 June, 2011. This conference will be held in Fukuoka, Japan, November 30 - December 2, 2011.
Wednesday, June 15, 2011
Call for papers: FUZZ-IEEE 2012
The deadline for papers submitted to the IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) is December 19, 2011. This conference is part of the 2012 IEEE World Congress on Computational Intelligence (WCCI 2012) and is held concurrently with the 2012 Congress on Evolutionary Computation (CEC) and the International Joint Conference on Neural Networks (IJCNN). WCCI 2012 will be held in Brisbane, Australia, June 10-15, 2012.
Conference paper deadline: ACAL 11
The deadline for papers submitted to the 5th Australian Conference on Artificial Life (ACAL) 2011 is 28 June 2011. This conference will be held in Perth, Australia, 6-8 December, 2011.
Paper submission deadline: UKCI 2011
The deadline for papers submitted to the 11th UK Workshop on Computational Intelligence (UKCI) 2011 is 20 June 2011. This workshop will be held in Manchester, UK, 7-9 September, 2011.
Paper submission deadline: ACIIDS 2012
The deadline for papers submitted to the 4th Asian Conference on Intelligent Information and Database Systems (ACIIDS) 2012 is September 15, 2011. This conference will be held in Kaohsiung, Taiwan, March 19-21, 2012.
Tuesday, June 14, 2011
Detecting reefs with ANN
I have just published a paper, along with several of my colleagues at the University of Adelaide, on detecting reefs using MLP.
The problem was that while there is coarse-scale bathymetric data from sonar surveys, and surveys of small areas that list the presence and absence of reefs in a relatively small number of points, there have not been large-scale surveys of where, exactly, reefs are. This is because the fine-scale sonar surveys needed to detect them remotely are very expensive and time consuming, and surveying manually (divers going into the water and looking) can be dangerous in places (either dangerous sea conditions, or big bitey beasties in the water). Not knowing where reefs are is a problem, especially if you want to construct ecological models of reef-dwelling creatures like abalone. In short, abalone like to live on reefs, so to build an accurate model, you must know where the reefs are.
We addressed this problem by firstly, processing the bathymetric data into slope and curvature measures of the sea bed, then training MLP over sliding 2D windows of these variables, where a known reef presence or absence was in the centre of the window. A window in this case was an n * n matrix of values, where we used n=5. So, the third element of the third row was the target cell, which the MLP was learning to classify as either a reef or non-reef point.
We found that combinations of the bathymetric value of the target cell, and a 5*5 window of seabed slope, gave us the best results. The overall experimental method we used was as I described in this post. While we weren't able to classify every reef exactly, the overall accuracy of 85% was enough to construct a useful map of reefs for ecological models of abalone.
We're looking at boosting the accuracy of our models by various means - this first paper is just a proof-of-concept, to show that we can find reefs with ANN.
The full citation for this paper is:
Watts, M.J., et al., A novel method for mapping reefs and subtidal rocky habitats using artificial neural networks. Ecological Modelling (2011), doi:10.1016/j.ecolmodel.2011.04.024
The problem was that while there is coarse-scale bathymetric data from sonar surveys, and surveys of small areas that list the presence and absence of reefs in a relatively small number of points, there have not been large-scale surveys of where, exactly, reefs are. This is because the fine-scale sonar surveys needed to detect them remotely are very expensive and time consuming, and surveying manually (divers going into the water and looking) can be dangerous in places (either dangerous sea conditions, or big bitey beasties in the water). Not knowing where reefs are is a problem, especially if you want to construct ecological models of reef-dwelling creatures like abalone. In short, abalone like to live on reefs, so to build an accurate model, you must know where the reefs are.
We addressed this problem by firstly, processing the bathymetric data into slope and curvature measures of the sea bed, then training MLP over sliding 2D windows of these variables, where a known reef presence or absence was in the centre of the window. A window in this case was an n * n matrix of values, where we used n=5. So, the third element of the third row was the target cell, which the MLP was learning to classify as either a reef or non-reef point.
We found that combinations of the bathymetric value of the target cell, and a 5*5 window of seabed slope, gave us the best results. The overall experimental method we used was as I described in this post. While we weren't able to classify every reef exactly, the overall accuracy of 85% was enough to construct a useful map of reefs for ecological models of abalone.
We're looking at boosting the accuracy of our models by various means - this first paper is just a proof-of-concept, to show that we can find reefs with ANN.
The full citation for this paper is:
Watts, M.J., et al., A novel method for mapping reefs and subtidal rocky habitats using artificial neural networks. Ecological Modelling (2011), doi:10.1016/j.ecolmodel.2011.04.024
Call for papers: IJCNN 2012
The deadline for papers submitted to the International Joint Conference on Neural Networks is December 19, 2011. This conference is part of the 2012 IEEE World Congress on Computational Intelligence (WCCI 2012) and is held concurrently with the 2012 Congress on Evolutionary Computation (CEC) and IEEE Conference on Fuzzy Logic (Fuzz-IEEE). WCCI 2012 will be held in Brisbane, Australia, June 10-15, 2012.
Monday, June 13, 2011
IJCNN 2011 Final Program
The final program for the 2011 International Joint Conference on Neural Networks (IJCNN) has been posted. This conference will be held in San Jose, California, July 31 - August 5, 2011.
Saturday, June 11, 2011
Call for papers: CEC 2012
The deadline for papers submitted to the 2012 Congress on Evolutionary Computation is December 19, 2011. This conference is part of the 2012 IEEE World Congress on Computational Intelligence (WCCI 2012) and is held concurrently with the 2012 International Joint Conference on Neural Networks (IJCNN) and IEEE Conference on Fuzzy Logic (Fuzz-IEEE). WCCI 2012 will be held in Brisbane, Australia, June 10-15, 2012.
Friday, June 10, 2011
Conference paper deadline: CIBCB 2012
The deadline for papers submitted to the 2012 conference on Computational Intelligence in Bioinformatics and Computational Biology is November 20, 2011. This conference will be held in San Diego, California, May 9-12, 2012.
Tuesday, May 31, 2011
Social Internetworking
I've just put online a brief description (PDF) of how I connect this blog to other social media sites, including LinkedIn, Twitter, and ResearchGATE.
I describe it as "Social Internetworking" (not an original phrase) and it involves using various free aggregators and web services to export blog posts.
You can follow me on Twitter at https://twitter.com/#!/DrMikeWatts, where you will see updates to this blog as soon as they are posted. You can find a complete list of my social networking profiles on my personal web page, mike.watts.net.nz.
I describe it as "Social Internetworking" (not an original phrase) and it involves using various free aggregators and web services to export blog posts.
You can follow me on Twitter at https://twitter.com/#!/DrMikeWatts, where you will see updates to this blog as soon as they are posted. You can find a complete list of my social networking profiles on my personal web page, mike.watts.net.nz.
Saturday, May 28, 2011
Fuzzy Markup Language
Giovanni Acampora describes the Fuzzy Markup Language (FML) in a series of articles. FML is a XML-based method for describing fuzzy logic systems. Fields in the schema specify the fuzzy knowledge base, which consists of the fuzzy variables and their membership functions, and the fuzzy rule base. The schema also allows for the specification of the inference and defuzzification method to use, and the type of fuzzy system (Zadeh-Mamdani or Takagi-Sugeno-Kang). Finally, it supports distributed fuzzy rule systems, that is, the user can specify the IP address of machines on which parts of the fuzzy system should run.
The major advantage of using XML to describe a fuzzy system is interoperability. All that is needed to read an XML file is the appropriate schema for that file, and an XML parser. This makes it much easier to exchange fuzzy systems between software: for example, an application could extract fuzzy rules from a neural network (like the EFuNN and SECoS rule extraction algorithms that exist) which could then be read directly into a fuzzy inference engine or uploaded into a fuzzy controller. Also, with technologies like XSLT, it is possible to compile the FML into the programming language of your choice, ready for embedding into whatever application you please.
Although Acampora's motivation for developing FML seems to be to develop embedded fuzzy controllers for ambient intelligence applications, FML could be a real boon for developers of fuzzy rule extraction algorithms: from my own experience during my PhD, I know that having to design a file format and implement the appropriate parsers for rule extraction and fuzzy inference engines can be a real pain, taking as much time as implementing the rule extraction algorithm itself. I would much rather have used something like FML for my work.
Such standard, XML-based file formats would be useful for other areas of computational intelligence: a standard XML format for ANN, for example, would be fairly simple to implement and also very useful. I could imagine, for example, training a MLP, saving it in an XML-based format, then using XSLT to transform it to C++ and uploading it into an embedded controller. Conventional, static-architecture ANN like perceptrons, MLP, or SOM could easily be represented in XML.
I will be watching for further developments in this area of technology: I've had quite enough of designing my own file formats!
The major advantage of using XML to describe a fuzzy system is interoperability. All that is needed to read an XML file is the appropriate schema for that file, and an XML parser. This makes it much easier to exchange fuzzy systems between software: for example, an application could extract fuzzy rules from a neural network (like the EFuNN and SECoS rule extraction algorithms that exist) which could then be read directly into a fuzzy inference engine or uploaded into a fuzzy controller. Also, with technologies like XSLT, it is possible to compile the FML into the programming language of your choice, ready for embedding into whatever application you please.
Although Acampora's motivation for developing FML seems to be to develop embedded fuzzy controllers for ambient intelligence applications, FML could be a real boon for developers of fuzzy rule extraction algorithms: from my own experience during my PhD, I know that having to design a file format and implement the appropriate parsers for rule extraction and fuzzy inference engines can be a real pain, taking as much time as implementing the rule extraction algorithm itself. I would much rather have used something like FML for my work.
Such standard, XML-based file formats would be useful for other areas of computational intelligence: a standard XML format for ANN, for example, would be fairly simple to implement and also very useful. I could imagine, for example, training a MLP, saving it in an XML-based format, then using XSLT to transform it to C++ and uploading it into an embedded controller. Conventional, static-architecture ANN like perceptrons, MLP, or SOM could easily be represented in XML.
I will be watching for further developments in this area of technology: I've had quite enough of designing my own file formats!
Tuesday, May 24, 2011
Evolving Connectionist Systems
An interesting family of neural networks is Evolving Connectionist Systems (ECoS). These were invented by Professor Nik Kasabov around 1998. ECoS are constructive networks, that is, they do not start with a fixed structure but instead grow (add neurons) as training data is presented to them. The advantages of this are:
The first ECoS was the Evolving Fuzzy Neural Network EFuNN. Later ECoS include the Simple Evolving Connectionist System SECoS (which is really an EFuNN with the fuzzy logic elements removed) and the Evolving Clustering Method ECM. EFuNN and SECoS both have rule extraction algorithms associated with them, by which fuzzy rules can be extracted from a trained EFuNN or SECoS network. This makes ECoS very useful for data mining, especially in an online application area.
I wrote a review of ECoS technology a couple of years ago, in this paper. An online reprint is available here. I also maintain a website of resources on ECoS networks at: ecos.watts.net.nz.
Research on ECoS networks is continuing, especially at Prof. Kasabov's lab KEDRI. Nowadays, ECoS research is focused on spiking neuron models, that is, neurons that include a temporal aspect to their activation, much as biological neurons do.
- they are fast learning, as they learn the data as it presented, rather than iteratively
- they are hard to over-train, as new data is accommodated by adding new neurons to the network
The first ECoS was the Evolving Fuzzy Neural Network EFuNN. Later ECoS include the Simple Evolving Connectionist System SECoS (which is really an EFuNN with the fuzzy logic elements removed) and the Evolving Clustering Method ECM. EFuNN and SECoS both have rule extraction algorithms associated with them, by which fuzzy rules can be extracted from a trained EFuNN or SECoS network. This makes ECoS very useful for data mining, especially in an online application area.
I wrote a review of ECoS technology a couple of years ago, in this paper. An online reprint is available here. I also maintain a website of resources on ECoS networks at: ecos.watts.net.nz.
Research on ECoS networks is continuing, especially at Prof. Kasabov's lab KEDRI. Nowadays, ECoS research is focused on spiking neuron models, that is, neurons that include a temporal aspect to their activation, much as biological neurons do.
Wednesday, May 18, 2011
Modelling distribution of jellyfish with ANN
A new paper first-authored by David Pontin, my ex-PhD student from Lincoln University. This describes how he used MLP to model to presence and absence of a species of stinging jellyfish (Physalia physalis) at New Zealand beaches.
There are a couple of interesting points about this paper. Firstly, because there have been no surveys of Physalia distribution, a surrogate data set was used. This data set was stings recorded by lifeguards of Surf Lifesaving New Zealand. Since lifeguards treat jellyfish stings, each incident has to be recorded, and Physalia is the only stinging organism in New Zealand waters, a fairly large data set was available as to the presence of these jellyfish. Predictions were made from oceanic variables such as wave height and direction, and wind speed and direction.
Secondly, the data was carefully cleaned: since stings of swimmers was used as the surrogate for Physalia presence, times when there were no swimmers at the beach were excluded from the data set. While this introduced a small missing-not-at-random bias, it also removed a large number of false absences: if an example was recorded as an absence, then it was because there were no stings recorded, not because there was no one in the water.
Thirdly, an analysis of the contributions of each input of the ANN was performed. This showed which of the oceanic variables contributed the most to the presence of Physalia. This analysis indicated that there may be a hitherto unknown spawning ground for this species in the Tasman Sea.
Finally, and this is in many ways the focus of the paper, the contribution analysis of the ANN was compared with the results of input contribution analysis by an evolutionary algorithm.
Overall, this is a nice little paper that neatly sums up David's work and contributes to the understanding of the behaviour of Physalia. This shows how useful computational intelligence is to ecological applications, an area where there is, in my opinion, enormous potential for computational intelligence researchers to make real, meaningful contributions.
There are a couple of interesting points about this paper. Firstly, because there have been no surveys of Physalia distribution, a surrogate data set was used. This data set was stings recorded by lifeguards of Surf Lifesaving New Zealand. Since lifeguards treat jellyfish stings, each incident has to be recorded, and Physalia is the only stinging organism in New Zealand waters, a fairly large data set was available as to the presence of these jellyfish. Predictions were made from oceanic variables such as wave height and direction, and wind speed and direction.
Secondly, the data was carefully cleaned: since stings of swimmers was used as the surrogate for Physalia presence, times when there were no swimmers at the beach were excluded from the data set. While this introduced a small missing-not-at-random bias, it also removed a large number of false absences: if an example was recorded as an absence, then it was because there were no stings recorded, not because there was no one in the water.
Thirdly, an analysis of the contributions of each input of the ANN was performed. This showed which of the oceanic variables contributed the most to the presence of Physalia. This analysis indicated that there may be a hitherto unknown spawning ground for this species in the Tasman Sea.
Finally, and this is in many ways the focus of the paper, the contribution analysis of the ANN was compared with the results of input contribution analysis by an evolutionary algorithm.
Overall, this is a nice little paper that neatly sums up David's work and contributes to the understanding of the behaviour of Physalia. This shows how useful computational intelligence is to ecological applications, an area where there is, in my opinion, enormous potential for computational intelligence researchers to make real, meaningful contributions.
Monday, May 16, 2011
Minimum Requirements for Computational Intelligence Papers
I am reposting this after it was lost during the Blogger meltdown last week.
In a previous post, I mentioned some challenges in reviewing computational intelligence papers. In this post, I list what I consider to be the minimum requirements for computational intelligence papers. These are the things that I look for when I review a paper, and if they aren't there, I reject it.
1. Define all variables in equations
While most computational intelligence papers have mathematics in them, a disappointingly large number of them do not define the variables in their equations. Or, if they do, they define them some distance from the equation itself. If I am reading your paper, I want to understand the maths, and I can't do that if I can't quickly find the meaning of each variable.
2. Use more than one data set to test an algorithm
If your paper describes a new algorithm, or even an improvement on an existing algorithm, it must be tested on more than one data set. The No Free Lunch theorem tells us that there are always some data sets on which every algorithm will perform well, and some on which it will perform poorly. While publication bias means that poor results often do not get reported, I do expect results over more than one data set.
3. Investigate more than one set of parameters
For any algorithm, there will be one set of parameters that yields better performance than others. This means that if your study only utilised a single set of parameters, you cannot tell whether you might have gotten better results using different parameters. For new algorithms, it is useful to show how sensitive the performance of the algorithm is to its parameters.
4. Clearly describe how the parameters were chosen
This is a particular problem with papers that describe applications of algorithms. In short, even if you only list the parameters that gave the best performance, you should still describe how you chose them. Choosing parameters by trial-and-error is fine, but you must say in the paper that that was how you chose your parameters. Also, LIST THE PARAMETERS IN THE PAPER! Being able to replicate experiments is at the very heart of science, and if you don't say what your parameters were, your experiments can't be replicated.
5. Use multiple partitions of the data set
Neural network papers are particularly bad for this. Often, the algorithm will be trained on one subset of the data (the training set) then tested on the remaining data (the testing or validation set, depending on who's writing the paper). Sometimes the data is divided into subsets randomly, sometimes it is not. There are two problems with this approach: firstly, it is entirely possible that the data is partitioned in a way that is particularly good for the algorithm, that is, the reported performance of the algorithm is due to the partitioning of the data, rather than the algorithm itself; Secondly, if the training parameters of the algorithm are chosen to maximise the performance over the testing set, that is equivalent to training over the testing set: that is, the testing set is no longer independent.
A better way (and my preferred technique) is to use k-fold cross-validation with an independent validation data set. In this technique, a validation data set is either randomly extracted or sourced separately from the training data set. The training data set is then divided into k-subsets, and the algorithm trained over k-1 of the subsets. The kth subset is then used to evaluate the performance of the algorithm. This is repeated k times, with a different subset held out as the evaluation set each time. This has the effect of training and testing over the entire data set. The results over the cross-validation are used to select the parameters, and the final performance is assessed over the validation data set. Since the validation data set is not used to select the parameters or to train the algorithm, it remains statistically independent.
6. The final testing / validation set must be independent
This means that the data in the validation set must be from a separate process to that which produced the data used for the k-fold cross-validation. If you are training an ANN to recognise speech, the validation set should be from a different speaker to those it was trained on, or at least from a different recording. If you are training an ANN to recognise spatial features, the validation data should come from a different area or different survey to the data that was used to train the ANN.
7. Compare a new algorithm with an existing algorithm
If you are claiming that your new algorithm work well and is highly accurate, then you need to prove that by comparing it against the performance of an existing, preferably well-known, algorithm. You don't need to perform the experiments with the existing algorithm yourself (although it is good if you do), you can point to previously published results. But a comparison must be carried out.
8. Comparisons of performance must be done in a statistically sound manner
This means that you can't just look at two numbers (two means) and say that your algorithm is better because the mean accuracy is higher than that of an existing algorithm. Comparisons must be done using statistical tests, that is, I want to know whether the results are significantly different. If you say that the results are significantly different, then you must also specify what statistical test was performance. For example, it is best to say something along the lines of "the accuracy of the Bogon 2000 algorithm was significantly higher than that of the Wibble 12 algorithm (two-tailed t-test, p=0.01)".
If you don't want to follow these principles, that's fine, as long as you explain in your paper (or review rejoinder) why you didn't do that. I'm quite prepared to be shown to be wrong.
In a previous post, I mentioned some challenges in reviewing computational intelligence papers. In this post, I list what I consider to be the minimum requirements for computational intelligence papers. These are the things that I look for when I review a paper, and if they aren't there, I reject it.
1. Define all variables in equations
While most computational intelligence papers have mathematics in them, a disappointingly large number of them do not define the variables in their equations. Or, if they do, they define them some distance from the equation itself. If I am reading your paper, I want to understand the maths, and I can't do that if I can't quickly find the meaning of each variable.
2. Use more than one data set to test an algorithm
If your paper describes a new algorithm, or even an improvement on an existing algorithm, it must be tested on more than one data set. The No Free Lunch theorem tells us that there are always some data sets on which every algorithm will perform well, and some on which it will perform poorly. While publication bias means that poor results often do not get reported, I do expect results over more than one data set.
3. Investigate more than one set of parameters
For any algorithm, there will be one set of parameters that yields better performance than others. This means that if your study only utilised a single set of parameters, you cannot tell whether you might have gotten better results using different parameters. For new algorithms, it is useful to show how sensitive the performance of the algorithm is to its parameters.
4. Clearly describe how the parameters were chosen
This is a particular problem with papers that describe applications of algorithms. In short, even if you only list the parameters that gave the best performance, you should still describe how you chose them. Choosing parameters by trial-and-error is fine, but you must say in the paper that that was how you chose your parameters. Also, LIST THE PARAMETERS IN THE PAPER! Being able to replicate experiments is at the very heart of science, and if you don't say what your parameters were, your experiments can't be replicated.
5. Use multiple partitions of the data set
Neural network papers are particularly bad for this. Often, the algorithm will be trained on one subset of the data (the training set) then tested on the remaining data (the testing or validation set, depending on who's writing the paper). Sometimes the data is divided into subsets randomly, sometimes it is not. There are two problems with this approach: firstly, it is entirely possible that the data is partitioned in a way that is particularly good for the algorithm, that is, the reported performance of the algorithm is due to the partitioning of the data, rather than the algorithm itself; Secondly, if the training parameters of the algorithm are chosen to maximise the performance over the testing set, that is equivalent to training over the testing set: that is, the testing set is no longer independent.
A better way (and my preferred technique) is to use k-fold cross-validation with an independent validation data set. In this technique, a validation data set is either randomly extracted or sourced separately from the training data set. The training data set is then divided into k-subsets, and the algorithm trained over k-1 of the subsets. The kth subset is then used to evaluate the performance of the algorithm. This is repeated k times, with a different subset held out as the evaluation set each time. This has the effect of training and testing over the entire data set. The results over the cross-validation are used to select the parameters, and the final performance is assessed over the validation data set. Since the validation data set is not used to select the parameters or to train the algorithm, it remains statistically independent.
6. The final testing / validation set must be independent
This means that the data in the validation set must be from a separate process to that which produced the data used for the k-fold cross-validation. If you are training an ANN to recognise speech, the validation set should be from a different speaker to those it was trained on, or at least from a different recording. If you are training an ANN to recognise spatial features, the validation data should come from a different area or different survey to the data that was used to train the ANN.
7. Compare a new algorithm with an existing algorithm
If you are claiming that your new algorithm work well and is highly accurate, then you need to prove that by comparing it against the performance of an existing, preferably well-known, algorithm. You don't need to perform the experiments with the existing algorithm yourself (although it is good if you do), you can point to previously published results. But a comparison must be carried out.
8. Comparisons of performance must be done in a statistically sound manner
This means that you can't just look at two numbers (two means) and say that your algorithm is better because the mean accuracy is higher than that of an existing algorithm. Comparisons must be done using statistical tests, that is, I want to know whether the results are significantly different. If you say that the results are significantly different, then you must also specify what statistical test was performance. For example, it is best to say something along the lines of "the accuracy of the Bogon 2000 algorithm was significantly higher than that of the Wibble 12 algorithm (two-tailed t-test, p=0.01)".
If you don't want to follow these principles, that's fine, as long as you explain in your paper (or review rejoinder) why you didn't do that. I'm quite prepared to be shown to be wrong.
Tuesday, May 10, 2011
Paper submission deadline: MLMI 2011
The deadline for papers submitted to the Second International Workshop on Machine Learning in Medical Imaging (MLMI 2o11) is June 1, 2011. This workshop will be held in Toronto, Canada, 18 September, 2011.
Monday, May 9, 2011
Paper submission deadline: AAIA'11
The deadline for submitting papers to the 6th International Symposium Advances in Artificial Intelligence and Applications (AAIA'11) is 31 May 2011. Symposium will be held in Szczecin, Poland, 19-21 September, 2011.
Sunday, May 8, 2011
Deadline for submission of extended abstracts: IEEE HST
The deadline for submission of extended abstracts to the 2011 IEEE Conference on Technologies for Homeland Security is May 13, 2011. If the abstract is accepted, a full paper must be submitted by June 24, 2011. This conference will be held in Greater Boston, 15-17 November, 2011.
Saturday, May 7, 2011
Submission deadline: EPIA 2011
The deadline for submission of abstracts to the XV Portuguese Conference on Artificial Intelligence is May 10 2011. This conference will be held in Lisbon, Portugal, 10-13 October, 2011.
Deadline extension: EA 2011
The deadline for the 2011 Artificial Evolution conference (EA2011) has been extended to 15 May 2011. This conference will be held in Angers, France, 24-26 October, 2011.
Friday, May 6, 2011
Peer review
Maggie Koerth-Baker writes about peer review at one of my favourite places on the web, Boing Boing. This article does a good job of describing peer review for the general public, especially in regards to why it's a good thing and what problems exist with it. As a working scientist, I have a slightly different point of view on peer review.
Firstly, most reviewers have the good intention of trying to make the paper better. This is something that many new authors don't get: they may even see the reviewers' comments as an attack on their competence. But that's seldom the case, at least not in my experience. Publishing bad papers, or papers with unreliable results, benefits no one. Whenever I review a paper, the first thing I ask myself is, "what can I suggest that could improve this paper?".
Secondly, reviewers have a lot of power. It seems to be the norm now that editors won't challenge anything a reviewer writes, even if it is egregiously wrong. If a reviewer criticizes an author on completely spurious grounds (for example, the reviewer is out of date in the field the paper is in, or if the reviewer simply doesn't know as much as they think they do) most editors will just allow the review through. This places the onus of disproving the reviewer on the author, which means authors have to spend time arguing with a reviewer (via the editor) instead of actually improving their paper.
Thirdly, reviewers do not have a lot of time. I've reviewed a lot of papers, more than a hundred, at last count, and to be honest, most of them sat on my desk for a few weeks before I managed to read them. Recently, the time frame to perform a review has been getting smaller, so there's even less time to do a quality review.
Computational intelligence papers have certain aspects that make them a challenge to review. Firstly, most have a fair amount of mathematics in them, but the number of authors who still don't define the variables in each equation is disappointingly large. Secondly, most papers have empirical work that test the proposed algorithms. But, a large proportion of those still don't produce statistically valid results - repeated trials, varied parameters, independent test sets, and statistical tests of significant differences over the results. I have noticed some progress on this in the last few years, but nowhere near as much as I would like.
I think I'll have to write this up in a future post...
Firstly, most reviewers have the good intention of trying to make the paper better. This is something that many new authors don't get: they may even see the reviewers' comments as an attack on their competence. But that's seldom the case, at least not in my experience. Publishing bad papers, or papers with unreliable results, benefits no one. Whenever I review a paper, the first thing I ask myself is, "what can I suggest that could improve this paper?".
Secondly, reviewers have a lot of power. It seems to be the norm now that editors won't challenge anything a reviewer writes, even if it is egregiously wrong. If a reviewer criticizes an author on completely spurious grounds (for example, the reviewer is out of date in the field the paper is in, or if the reviewer simply doesn't know as much as they think they do) most editors will just allow the review through. This places the onus of disproving the reviewer on the author, which means authors have to spend time arguing with a reviewer (via the editor) instead of actually improving their paper.
Thirdly, reviewers do not have a lot of time. I've reviewed a lot of papers, more than a hundred, at last count, and to be honest, most of them sat on my desk for a few weeks before I managed to read them. Recently, the time frame to perform a review has been getting smaller, so there's even less time to do a quality review.
Computational intelligence papers have certain aspects that make them a challenge to review. Firstly, most have a fair amount of mathematics in them, but the number of authors who still don't define the variables in each equation is disappointingly large. Secondly, most papers have empirical work that test the proposed algorithms. But, a large proportion of those still don't produce statistically valid results - repeated trials, varied parameters, independent test sets, and statistical tests of significant differences over the results. I have noticed some progress on this in the last few years, but nowhere near as much as I would like.
I think I'll have to write this up in a future post...
Thursday, May 5, 2011
Ten rules for good writing
Henry Gee writes about The ten rules for excellent writing. Not that there's actually ten rules in the article, but it's a nice title. The rules he does discuss are:
Rule 1: Write Every Day
Rule 2: Write as you would speak
Rule 3: Stick to the point
Rule 4: Take A Break
Rule 5: Finish it
Rule 6: Avoid cliché
I am trying to follow Rule 1 more often: this blog helps, and I also have a backlog of papers to deal with.
Rule 2 ties back to the idea of having a narrative in scientific papers, as discussed in this post. Scientific articles do expect a certain level of formality and a certain writing style: I have even heard of an author having to fight to get a journal to accept an article written in the active voice.
Sticking to the point (Rule 3) isn't all that hard for me, but I know I can improve - I have been told that my writing is a bit "information light".
Take a break (Rule 4) - always a good idea, and the best thing about having multiple projects on the go is that you can take a break from one project by working on another. That way, you are getting being productive while taking a break.
I also need to follow Rule 5 with more care: my backlog of papers isn't getting any smaller. One pitfall with this in science is that most papers have multiple authors, and they tend to be just as busy, if not more so, than you are. So, papers get delayed, because your coauthors don't have time to deal with them. One tactic I have found useful to is set a deadline: if they don't get back to you before the deadline, you assume that the paper is OK and can be submitted as is.
Rule 6 - are there cliches in scientific writing? Submit your favourites in the comments.
Rule 1: Write Every Day
Rule 2: Write as you would speak
Rule 3: Stick to the point
Rule 4: Take A Break
Rule 5: Finish it
Rule 6: Avoid cliché
I am trying to follow Rule 1 more often: this blog helps, and I also have a backlog of papers to deal with.
Rule 2 ties back to the idea of having a narrative in scientific papers, as discussed in this post. Scientific articles do expect a certain level of formality and a certain writing style: I have even heard of an author having to fight to get a journal to accept an article written in the active voice.
Sticking to the point (Rule 3) isn't all that hard for me, but I know I can improve - I have been told that my writing is a bit "information light".
Take a break (Rule 4) - always a good idea, and the best thing about having multiple projects on the go is that you can take a break from one project by working on another. That way, you are getting being productive while taking a break.
I also need to follow Rule 5 with more care: my backlog of papers isn't getting any smaller. One pitfall with this in science is that most papers have multiple authors, and they tend to be just as busy, if not more so, than you are. So, papers get delayed, because your coauthors don't have time to deal with them. One tactic I have found useful to is set a deadline: if they don't get back to you before the deadline, you assume that the paper is OK and can be submitted as is.
Rule 6 - are there cliches in scientific writing? Submit your favourites in the comments.
Wednesday, May 4, 2011
Conference paper deadline: iCAST 2011
The deadline for submitting papers to the 3rd International Conference on Awareness Science and Technology (iCAST 2011) is June 1, 2011. This conference is co-sponsored by the IEEE Computational Intelligence Society and will be held in Dalian, China, September 27-30, 2011.
Tuesday, May 3, 2011
IEEE Computational Intelligence Society Social Media Presences
The Computational Intelligence Society of the IEEE now has presences on social media sites:
Twitter
Facebook
LinkedIn
These presences result from the work of the Computational Intelligence Society's Social Media Subcommittee, which I have the privilege of serving on.
These presences result from the work of the Computational Intelligence Society's Social Media Subcommittee, which I have the privilege of serving on.
Conference paper deadline: ICAIS 2011
The deadline for submitting papers to the International Conference on Adaptive and Intelligent Systems 2011 (ICAIS 2011) is June 10, 2011. This conference is co-sponsored by the IEEE Computational Intelligence Society and will be held in Klagenfurt, Austria, September 6-8, 2011.
Monday, May 2, 2011
Competition: describe fuzzy logic in a video
Via the IEEE Computational Intelligence Society's Twitter feed comes word of the following competition: Create a video that explains fuzzy logic and its applications to an audience of high school students or the general public in a format suitable for posting on YouTube.
First prize is $3000, second prize is $2000 and third prize is $1000. Interest must be registered by the 10th of June and the deadline for submitting videos is the 10th of September.
First prize is $3000, second prize is $2000 and third prize is $1000. Interest must be registered by the 10th of June and the deadline for submitting videos is the 10th of September.
Sunday, May 1, 2011
Call for second-round submissions: ICNS'11-FSKD'11
The deadline for second-round submissions to the The 7th International Conference on Natural Computation and The 8th International Conference on Fuzzy Systems and Knowledge Discovery (ICNS'11-FSKD'11) is 16 May 2011. These conferences will be held jointly in Shanghai, China, 26-28 July, 2011.
Saturday, April 30, 2011
Science writing doesn't have to be boring writing
A brief article by Jo Marchant at the Guardian shows that scientific writing doesn't have to be dry and boring.
Writing scientific papers is an essential part of any scientist's job. They are the primary means by which scientists communicate their techniques and findings to other scientists, and they are increasingly becoming the primary metric by which the value of a scientist is measured. During my career, I've read probably thousands of published papers, reviewed about a hundred papers as part of the peer-review process, and written more than fifty papers of my own. But how many of them were written really well? Not many at all - and I include my own papers in this statement, some of which send even me to sleep.
Scientific writing does need to be as unambiguous of possible, and computational intelligence papers have the disadvantage of often requiring a fair amount of mathematics. But is it really that difficult to introduce more of a narrative to our papers? And would reviewers allow such papers to be published?
Writing scientific papers is an essential part of any scientist's job. They are the primary means by which scientists communicate their techniques and findings to other scientists, and they are increasingly becoming the primary metric by which the value of a scientist is measured. During my career, I've read probably thousands of published papers, reviewed about a hundred papers as part of the peer-review process, and written more than fifty papers of my own. But how many of them were written really well? Not many at all - and I include my own papers in this statement, some of which send even me to sleep.
Scientific writing does need to be as unambiguous of possible, and computational intelligence papers have the disadvantage of often requiring a fair amount of mathematics. But is it really that difficult to introduce more of a narrative to our papers? And would reviewers allow such papers to be published?
Friday, April 29, 2011
Conference paper deadline: SMAP 2011
The paper submission deadline for the 6th International Workshop on Semantic Media Adaptation and Personalization (SMAP 2011) is May 10, 2011. This workshop is co-sponsored by the IEEE Computational Intelligence Society and will be held in Vigo, Spain, December 1-2, 2011.
Thursday, April 28, 2011
Conference paper deadline: ICIC 2011
The deadline for paper submitted to the 2011 International Conference on Intelligent Computing (ICIC 2011) is May 20, 2011. This deadline has been shifted back from April 20. The date for notification of paper acceptance is April 30, so time travel may be involved. This conference will be held in Zhengzhou, China, August 11 - 14, 2011.
Wednesday, April 27, 2011
Conference submission deadline: INMIC 2011
The deadline for abstracts submitted to the 2011 14th International Multitopic Conference (INMIC) is June 10 2011. This conference deals with a wide range of topics (hence the name) including artificial intelligence and fuzzy systems. The conference will be held in Karachi, Pakistan, December 22-24, 2011.
Tuesday, April 26, 2011
Conference paper deadline: CSE-11
The deadline for papers submitted to the ICGST International Conference on Computer Science and Engineering 2011 (CSE-11) is 15 August 2011. This conference will be held in Istanbul, Turkey, 19-21 December, 2011.
Tuesday, April 19, 2011
Registration for IJCNN 2011 Open
Registration for the 2011 International Joint Conference on Neural Networks is now open. This conference will be held in San Jose, California, 31 July - 5 August, 2011.
Register at http://www.ijcnn2011.org/registration.php by June 30 for a reduced rate.
IJCNN is one of the leading conference on artificial neural networks. It is jointly sponsored by the International Neural Network Society (INNS) and the IEEE Computational Intelligence Society.
Register at http://www.ijcnn2011.org/registration.php by June 30 for a reduced rate.
IJCNN is one of the leading conference on artificial neural networks. It is jointly sponsored by the International Neural Network Society (INNS) and the IEEE Computational Intelligence Society.
Sunday, April 17, 2011
Upcoming webinar
From the IEEE computational intelligence society:
IEEE CIS Webinar
Title: "Type-2 Fuzzy Logic Controllers: A way Forward for Fuzzy Systems in Real World Environments"
Speaker: Prof. Hani Hagras, School of Computer Science and Electronic Engineering, University of Essex (UK)
Date: April 26, 2011, Tuesday
Time: 10:00 a.m. – 11:30 p.m. (EDT) (i.e., Toronto, Ontario) or 3:00 p.m.– 4:30 p.m. (BST, i.e., British Summer Time) (i.e., London, UK)
Website:http://ieee-cis.org/members/webinars/
IEEE CIS Webinar
Title: "Type-2 Fuzzy Logic Controllers: A way Forward for Fuzzy Systems in Real World Environments"
Speaker: Prof. Hani Hagras, School of Computer Science and Electronic Engineering, University of Essex (UK)
Date: April 26, 2011, Tuesday
Time: 10:00 a.m. – 11:30 p.m. (EDT) (i.e., Toronto, Ontario) or 3:00 p.m.– 4:30 p.m. (BST, i.e., British Summer Time) (i.e., London, UK)
Website:
Thursday, April 14, 2011
FuzzyCOPE 3
After many years of being absent from the web, the FuzzyCOPE 3 website is now back online.
I developed FuzzyCOPE 3 at the University of Otago in 1998-1999. FuzzyCOPE 3 is an integrated environment for data processing and fuzzy-neural network modelling. After I left Otago, it was taken off of the web, but I've noticed that people are still searching for it. So, for historical reasons, I have decided to put it back up. There won't be any more bug fixes or updates, but hopefully people will find it useful. Also, there probably won't be a FuzzyCOPE 4, unless someone wants to pay me to do it.
The new address for FuzzyCOPE 3 is http://software.watts.net.nz/FuzzyCOPE3/
A paper describing FuzzyCOPE 3 is available here. The complete citation for this paper is:
1999 - Watts, M., Woodford, B., and Kasabov N., FuzzyCOPE - A Software Environment for Building Intelligent Systems - the Past, the Present and the Future, in: Emerging Knowledge Engineering and Connectionist-based Systems, Proceedings of the ICONIP/ANZIIS/ANNES’99 Workshop "Future directions for intelligent systems and information sciences", Dunedin, 22-23 Nov.1999, N.Kasabov and K.Ko (eds) 188-192.
I developed FuzzyCOPE 3 at the University of Otago in 1998-1999. FuzzyCOPE 3 is an integrated environment for data processing and fuzzy-neural network modelling. After I left Otago, it was taken off of the web, but I've noticed that people are still searching for it. So, for historical reasons, I have decided to put it back up. There won't be any more bug fixes or updates, but hopefully people will find it useful. Also, there probably won't be a FuzzyCOPE 4, unless someone wants to pay me to do it.
The new address for FuzzyCOPE 3 is http://software.watts.net.nz/FuzzyCOPE3/
A paper describing FuzzyCOPE 3 is available here. The complete citation for this paper is:
1999 - Watts, M., Woodford, B., and Kasabov N., FuzzyCOPE - A Software Environment for Building Intelligent Systems - the Past, the Present and the Future, in: Emerging Knowledge Engineering and Connectionist-based Systems, Proceedings of the ICONIP/ANZIIS/ANNES’99 Workshop "Future directions for intelligent systems and information sciences", Dunedin, 22-23 Nov.1999, N.Kasabov and K.Ko (eds) 188-192.
Saturday, April 2, 2011
Conference paper deadline: AI 2011
The deadline for papers submitted to the 24th Australasian Joint Conference on Artificial Intelligence (AI 2011) is 28 June 2011. This conference will be held in Perth, Western Australia, 5th to 8th December, 2011.
Thursday, March 24, 2011
Conference paper deadline: IEEE CIFEr 2012
The deadline for papers submitted to the IEEE Computational Intelligence in Financial Engineering and Economics Conference, 2012 (CIFEr 2012) is 21 October, 2011. This conference will be held in New York City, 30 March 2012.
Conference paper deadline: WCCI 2012
The deadline for papers submitted to the World Congress on Computational Intelligence 2012 (WCCI 2012) is 19 December 2011. This conference will beheld in Brisbane, Australia, 10 - 15 June, 2012.
WCCI combines three conferences: the International Joint Conference on Neural Networks (IJCNN); IEEE Conference on Fuzzy Logic (Fuzz-IEEE); and the Congress on Evolutionary Computation (CEC). One registration fee provides access to all three conferences.
WCCI combines three conferences: the International Joint Conference on Neural Networks (IJCNN); IEEE Conference on Fuzzy Logic (Fuzz-IEEE); and the Congress on Evolutionary Computation (CEC). One registration fee provides access to all three conferences.
Tuesday, March 22, 2011
Conference paper deadline: IWACI 2011
The deadline for papers submitted to the International Workshop on Advanced Computational Intelligence 2011 (IWACI 2011) is 1 July, 2011. This conference will be held in Wuhan, China, 19 - 21 October, 2011.
Monday, March 21, 2011
Conference paper deadline: CACS 2011
The deadline for papers submitted to the 2nd International Congress on Computer Applications and Computational Science 2011 (CACS 2011) is 15 May 2011. Among the many topics covered by this conference are data mining intelligence systems. This conference will be held in Bali, Indonesia, 15 - 17 November, 2011.
Sunday, March 20, 2011
Conference paper deadline: TENCON 2011
The deadline for paper submission to the IEEE Region 10 Conference (IEEE TENCON) 2011 is 1st May, 2011. This conference will be held 21 - 24 November in Bali, Indonesia.
Updated website on Evolving Connectionist Systems
I have just updated the Literature section on the website Evolving Connectionist Systems. There are many new references to papers on the algorithms and applications of evolving connectionist systems.
Saturday, March 19, 2011
Conference submission deadline: Neuroinformatics 2011
The deadline for submission of abstracts to Neuroinformatics 2011 is April 19, 2011. This conference will be held in Boston, USA, 4 - 6 September, 2011.
Thursday, March 17, 2011
Conference paper deadline: IEEE CIMSA 2011
The deadline for abstracts submitted to the IEEE International Conference on Computational Intelligence for Measurement Systems and Applications 2011 (IEEE CIMSA 2011) is 15 April 2011. This conference will be held in Ottawa, Canada, 19 - 21 September, 2011.
Wednesday, March 16, 2011
Conference paper deadline: IEEE CIG 2011
The deadline for papers submitted to the IEEE Conference on Computational Intelligence in Games (IEEE CIG 2011) is 30 March 2011. This conference will be held in Seoul, Korea, 31 August to 3 September, 2011.
Friday, February 11, 2011
Conference paper deadline: RAICS 2011
The deadline for papers submitted to the IEEE Recent Advances in Intelligent Computational Systems (RAICS) 2011 is 28 February 2011. This conference will be held in Thiruvananthapuram, India, 22-24 September, 2011.
Friday, January 28, 2011
Conference paper deadline: KES 2011
The deadline for papers submitted to the 15th conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2011) is March 1st 2011. This conference will be held in Kaiserslautern, Germany, 12-14 September, 2011.
Tuesday, January 25, 2011
Conference paper deadline: ICARIS 2011
The paper submission deadline for the 10th International Conference on Artificial Immune Systems (ICARIS 2011) is 28th February 2011. This conference will be held at the University of Cambridge, UK, 18-21 July, 2011.
Tuesday, January 11, 2011
Conference paper deadline: ICONIP 2011
The paper submission deadline for the International Conference on Neural Information Processing (ICONIP) 2011 is June 1, 2011. This conference will be held in Shanghai, China, November 14-17, 2011.
Sunday, January 9, 2011
Associate Professor Mark Laws
I returned home from holiday yesterday to the heart-breaking news that Associate Professor Mark Laws had drowned. He leaves behind his wife, three daughters and five grandchildren.
Mark was a gifted researcher, a loving and devoted husband and father, and my friend.
Mark and I did our PhDs together in the old Knowledge Engineering Lab at the University of Otago. For years we shared an office, worked together, and partied together. With a handful of others from the lab, he made my time as a post-grad not only bearable, but fun.
He was devoted to his family - I still remember how proud he was of his daughters achievements, and how happy he was when his first grand-child was born. It's for them that I feel the most.
Over the last few years we hadn't seen each other as much as we would have liked, but every time I saw him, he had a big smile and welcoming hug for me. I learned so much from him and I'm immensely grateful to have had him in my life.
I still can't believe that he's gone.
Mark was a gifted researcher, a loving and devoted husband and father, and my friend.
Mark and I did our PhDs together in the old Knowledge Engineering Lab at the University of Otago. For years we shared an office, worked together, and partied together. With a handful of others from the lab, he made my time as a post-grad not only bearable, but fun.
He was devoted to his family - I still remember how proud he was of his daughters achievements, and how happy he was when his first grand-child was born. It's for them that I feel the most.
Over the last few years we hadn't seen each other as much as we would have liked, but every time I saw him, he had a big smile and welcoming hug for me. I learned so much from him and I'm immensely grateful to have had him in my life.
I still can't believe that he's gone.
Friday, December 24, 2010
Conference paper deadline: ICOMLAI 2011
The paper submission deadline for the International Conference on Machine Learning and Artificial Intelligence (ICOMLAI) 2011 is February 1st, 2011. This conference will be held in Penang, Malaysia, June 1-2 2011.
Wednesday, December 15, 2010
Conference paper deadline: IWANN 2011
The paper submission deadline for the International Workshop on Artificial Neural Networks 2011 (IWANN 2011) is 21 January 2011. This workshop will be held in Torremolinos, Spain, 8-10 June, 2011.
Conference paper deadline: CISIS'11
The paper submission deadline for the 4th annual conference on Computational Intelligence in Security for Information Systems 2011 (CISIS'11) is 21 January 2011. This conference will be held in Torremolinos, Spain, 8-10 June 2011.
Wednesday, December 8, 2010
Call for papers: CDMC 2011
Posted by request of Dr Paul S. Pang of the Unitec Institute of Technology, New Zealand, and the Knowledge Engineering and Discovery Research Institute (KEDRI) at Auckland University of Technology (AUT).
The competition is associated with the 4th International Cybersecurity and Data Mining workshop (CDM2011), which is an associated event to the 18th International Conference on Neural Information Processing (ICONIP2011), Shanghai, China, November 14 - 17 2011.
The entry is open to researchers from community at large. The proceedings of the competition is planned to be published in a journal special issue—details of this is to be determined.
Venue: Hang Zhou, reputed as Silicon Valley in Paradise, is one of the important tourist attractions in China for its natural beauty and historical and cultural heritages. The workshop will be held on 18th, November 2011 (Friday) in Hang Zhou, China.
Objectives: The purpose of the 2nd ICONIP Cybersecurity Data Mining Competition is to increase awareness of Cybersecurity and the potential of industrial applications, and to give young researchers exposure to the main issues related to the topic and to ongoing work in this area. The focus of this competition is on string sequences analysis towards application of knowledge discovery techniques for protecting personal computer information by means of detection, prevention, and response to various attacks.
Prizes and Awards: We have set prizes for the competition. The top ranking teams of all 3 data mining tasks will be eligible to win a cash prize of NZ $3000. Additional prize may be available as travel grants for deserving participants to help them attend the ICONIP2011 conference and/or the CDM2011 workshop.
Paper submissions and publications: Papers for method description of up to 8 pages are required to be submitted online following the Springer LNCS format. Selected and extended papers will be published in special issues of international journals after the conference. Posters are expected to be in A1 size to fit our boards, otherwise they may not be displayed in poster session.
Deadline for submission: The final submission deadline is the 31st of July 2011, and the competition results will be announced by the 18th, November 2011.
The competition is associated with the 4th International Cybersecurity and Data Mining workshop (CDM2011), which is an associated event to the 18th International Conference on Neural Information Processing (ICONIP2011), Shanghai, China, November 14 - 17 2011.
The entry is open to researchers from community at large. The proceedings of the competition is planned to be published in a journal special issue—details of this is to be determined.
Venue: Hang Zhou, reputed as Silicon Valley in Paradise, is one of the important tourist attractions in China for its natural beauty and historical and cultural heritages. The workshop will be held on 18th, November 2011 (Friday) in Hang Zhou, China.
Objectives: The purpose of the 2nd ICONIP Cybersecurity Data Mining Competition is to increase awareness of Cybersecurity and the potential of industrial applications, and to give young researchers exposure to the main issues related to the topic and to ongoing work in this area. The focus of this competition is on string sequences analysis towards application of knowledge discovery techniques for protecting personal computer information by means of detection, prevention, and response to various attacks.
Prizes and Awards: We have set prizes for the competition. The top ranking teams of all 3 data mining tasks will be eligible to win a cash prize of NZ $3000. Additional prize may be available as travel grants for deserving participants to help them attend the ICONIP2011 conference and/or the CDM2011 workshop.
Paper submissions and publications: Papers for method description of up to 8 pages are required to be submitted online following the Springer LNCS format. Selected and extended papers will be published in special issues of international journals after the conference. Posters are expected to be in A1 size to fit our boards, otherwise they may not be displayed in poster session.
Deadline for submission: The final submission deadline is the 31st of July 2011, and the competition results will be announced by the 18th, November 2011.
Conference paper deadline: KES-AMSTA-11
The paper submission deadline for the KES Conference on Agents and Multi-agent Systems - Technologies and Applications (KES-AMSTA) 2011 is 20 December 2010. This conference will be held in Manchester, UK, 29 June - 1 July, 2011.
Tuesday, December 7, 2010
Guest post: WCCI Conference Report
This is a guest post by my colleague and friend Dr Brendon Woodford of the Department of Information Science at the University of Otago. Brendon writes about the 2010 World Congresss on Computational Intelligence, which was held in Barcelona, Spain, July 18-23.
The 2010 IEEE World Congress on Computational Intelligence (WCCI'2010) was held at the Centre De Convencions Internacional De Barcelona, Barcelona, Spain, between the 18th and 23rd of July, 2010. This conference, held biyearly, is a combination of IEE The International Joint Conference on Neural Networks (IJCNN), the IEEE International Conference on Fussy Systems (Fuzz-IEEE), and the IEEE Congress on Evolutionary Computation (CEC). A total of 1715 papers were presented over five days with up to 17 parallel sessions going on at any one time. At a guess there were over 2000 delegates at the congress itself.
Prior to the conference proper, a set of tutorials on the Sunday was presented on a wide range on topics from an introduction to evolutionary game theory to the foundations of computational intelligence in the context of knowledge-based medicine.
The main highlight of the Sunday evening was the Welcome Reception at the Convention Centre itself which enabled me and my colleagues to catch up with old friends and make new connections.
Most of the plenary sessions were held mid-morning across the week. Monday's plenary was presented by Dr. Sushmita Mitra on hybridization with rough sets, Prof. Dr. Habil. Rudolf Kruse talked on Temporal Aspects in Data Mining at the Tuesday plenary, Prof. Dr. Pedro Larrañaga spoke on probabilistic graphical models and evolutionary computation, an in-depth talk on The evolution of fuzzy clustering was presented by Dr. Enrique H. Ruspini, and finally Dr. Shiro Usui presented on the PLATO platform for collaborative brain system modeling. My impression from these talks was that the themes of hybrid techniques applied to real-world problems appeared to be a strong thread across all the talks.
In terms of the paper presentations, most of the subject matter ranged from the development or extension to theories of computational intelligence to applications of existing techniques to real-world problems. An emerging thread of some of the presentations which I had not been party to was the emphasis on how such work has been targeted to industry with a few to create stronger links between the research community and big business. This concept was cemented in a panel session on "Computational Intelligence in Industry: Promises and Challenges" which presented some cases studies on how research groups around the world have forged links with corporations to better their business.
The gala dinner was not held at the conference venue but at Alfonso XIII's Palace, in the Fira of Barcelona, a majestic building which hosted all delegates in its vast dining space. As part of the event, an ceremony was held to honour outstanding research with such categories as the Best Paper Awards.
The final social event I could attend was the Concert at the “Palau de la Música Catalanathe” in which the Camera Musicae Orquestra performed "The Eight Seasons"; a variation of Vivaldi's Four Seasons which each original movement accompanied by an extra movement by composer Astor Piazzolla (1921-1992). Although I could not make it myself, I was reliably informed that it was a world class performance.
Images of the more social parts of the conference can be found at http://www.wcci2010.org/photo-gallery
The presentation of my IJCNN accepted paper was held directly after lunch on the last day of the conference. Although the numbers of delegates had dwindled over the week, there was still enough in attendance to provide me with good feedback on the presented work.
Friday, November 26, 2010
Conference paper deadline: KES-IDT-11
The deadline for submitting papers to the 3rd International Conference on Decision Technologies 2011 (KES-IDT-11) is 1st February 2011. This conference will be held at the University of Piraeus, Piraeus, Greece, 20-22 July 2011.
Friday, November 19, 2010
Call for papers: ICCCI 2011
The deadline for papers submitted to the International Conference on Collective Intelligence (ICCCI) 2011 is 15 March 2011. The conference will be held in Gdynia, Poland, 21-23 September, 2011.
Thursday, November 18, 2010
Missing Value Imputation
An interesting paper in Neural Networks: "Missing value imputation on missing completely at random data using multilayer perceptrons" by Esther-Lydia Silva-RamÃreza, Rafael Pino-MejÃasb, Manuel López-Coelloa, and MarÃa-Dolores Cubiles-de-la-Vegac.
In short, they have demonstrated that MLP can be used to impute values that are randomly missing from data sets. They also examine which learning algorithms and network architecture give the best results.
One thing that I would be interested in finding out, though, is how well an ANN trained on the imputed data would perform. In other words, in a situation where you had to impute data to train an ANN, how well would that ANN perform compared to one trained on the complete data set?
In short, they have demonstrated that MLP can be used to impute values that are randomly missing from data sets. They also examine which learning algorithms and network architecture give the best results.
One thing that I would be interested in finding out, though, is how well an ANN trained on the imputed data would perform. In other words, in a situation where you had to impute data to train an ANN, how well would that ANN perform compared to one trained on the complete data set?
Friday, November 12, 2010
Congratulations to Professor Warren Tate, of the Department of Biochemistry at my alma mater the University of Otago, who has been awarded the Rutherford Medal, New Zealand's highest award for scientific research.
Professor Tate and I published some work together (alternative link) several years ago, and apart from being a top scientist, he is also a very nice guy.
Professor Tate and I published some work together (alternative link) several years ago, and apart from being a top scientist, he is also a very nice guy.
Thursday, October 28, 2010
Call for papers: IWANN 2011
This is posted at the request of Dr Leonardo Franco. The International Work Conference in Artificial Neural Networks 2011 (IWANN 2011) will be held in Torremolinos, Spain, 8-10 June 2011.
Call for papers Iwann 2011
The IWANN biennial meeting seeks to provide a discussion forum for scientists, engineers, educators and students about the latest ideas and realizations in the foundations, theory, models and applications of hybrid systems inspired on nature (neural networks, fuzzy logic and evolutionary systems) as well as in emerging areas related to the above items. As in previous editions of IWANN, it also aims to create a friendly environment that could lead to the establishment or strengthening of scientific collaborations and exchanges among attendees.
During the present edition, the following associated satellite Workshops
will be organized:
The proceedings will include all the presented communications to the conference. As in previous editions of IWANN, we are arranging the publication of the proceedings with Springer-Verlag on Lecture Notes on Computer Science (LNCS) series, and the books will be available on-site. It is also foreseen the publication of an extended version of selected papers in a special issue on several specialized journals (such as Neurocomputing, Elsevier).
IWANN is included in the ranking of the best conferences established by the Computer Science Conference Ranking based on the "Estimated Impact of Conference (EIC,2009)", concretely in position 55 among 701 considered (in the Artificial Intelligence field), and in the rank B in Computing Research and Education Association (CORE). Also the IWANN papers are indexed by CiteSeer.IST, and by the organization Computing Research and Education Association (CORE).
Call for papers Iwann 2011
The IWANN biennial meeting seeks to provide a discussion forum for scientists, engineers, educators and students about the latest ideas and realizations in the foundations, theory, models and applications of hybrid systems inspired on nature (neural networks, fuzzy logic and evolutionary systems) as well as in emerging areas related to the above items. As in previous editions of IWANN, it also aims to create a friendly environment that could lead to the establishment or strengthening of scientific collaborations and exchanges among attendees.
During the present edition, the following associated satellite Workshops
will be organized:
- CISIS'11 4th International Conference on Computational Intelligence in Security for Information Systems
- ISCIF'11 - 1st International Workshop of Intelligent systems for context-based information fusion
- IWAAL'11 - III International Workshop on Ambient Assisted Living
The proceedings will include all the presented communications to the conference. As in previous editions of IWANN, we are arranging the publication of the proceedings with Springer-Verlag on Lecture Notes on Computer Science (LNCS) series, and the books will be available on-site. It is also foreseen the publication of an extended version of selected papers in a special issue on several specialized journals (such as Neurocomputing, Elsevier).
IWANN is included in the ranking of the best conferences established by the Computer Science Conference Ranking based on the "Estimated Impact of Conference (EIC,2009)", concretely in position 55 among 701 considered (in the Artificial Intelligence field), and in the rank B in Computing Research and Education Association (CORE). Also the IWANN papers are indexed by CiteSeer.IST, and by the organization Computing Research and Education Association (CORE).
Wednesday, September 29, 2010
Conference paper deadline: FUZZ-IEEE 2011
The paper submission deadline for the 2011 IEEE Conference on Fuzzy Systems (FUZZ-IEEE 2011) is January 15 2011. This conference will be held in Taipei, Taiwan (ROC) from 27-30 June, 2011.
Conference paper deadline: CEC 2011
The deadline for submitting paper to the 2011 Congress on Evolutionary Computation is 15 January, 2011. This conference will be held in New Orleans, Louisiana, June 5 - 8, 2011.
Conference paper deadline: IJCNN 2011
The deadline for papers submitted to the International Joint Conference on Neural Networks (IJCNN) 2011 is February 1, 2011. IJCNN will be held July 31 - August 5 in San Jose, California.
IJCNN is one of the premier conference on neural networks and is well worth attending.
IJCNN is one of the premier conference on neural networks and is well worth attending.
Monday, September 27, 2010
Academic publishing
An excellent essay by Phil Clapham on the need for academics to publish their research. One of his rules, that I am trying to apply to my own work, is to have at least one paper under review at any given time.
This means, though, that I should also be writing at least one paper at any given time, while also generating sufficient publishable results for at least one paper at any given time.
While this does encourage the practice of breaking research projects into small, easily published chunks, I suspect it may also encourage further proliferation of single publon papers.
This means, though, that I should also be writing at least one paper at any given time, while also generating sufficient publishable results for at least one paper at any given time.
While this does encourage the practice of breaking research projects into small, easily published chunks, I suspect it may also encourage further proliferation of single publon papers.
Conference paper deadline: KES AMSTA 2011
The deadline for submitting papers to the 5th International KES Symposium on Agents and Multi-agent Systems – Technologies and Applications (KES AMSTA 2011) is 20 December 2010. This conference will be held in Manchester, UK, 29 June - 1 July, 2011.
Wednesday, September 15, 2010
Conference paper deadline: INNS-IESNN
The deadline for papers submitted to the 2011 International Neural Network Society International Educational Symposium on Neural Networks is 30 September 2010. This conference will be held in Lima, Peru, 25-27 January, 2011.
This symposium is sponsored by the International Neural Network Society.
This symposium is sponsored by the International Neural Network Society.
Thursday, June 24, 2010
Conference paper deadline: NaBIC 2010
The paper submission deadline for the second conference on Nature and Biologically Inspired Computing (NABIC) 2010 is 15 August 2010. This conference will be held in Kitakyushu, Japan, December 15-17, 2010.
The first international conference I ever attended was held in Kitakyushu, in 1998. It is a very nice city, although I would recommend getting a hotel away from the rail lines: the freight trains run all night!
The first international conference I ever attended was held in Kitakyushu, in 1998. It is a very nice city, although I would recommend getting a hotel away from the rail lines: the freight trains run all night!
Wednesday, June 23, 2010
New Website on Evolving Connectionist Systems
I've just launched a website on Evolving Connectionist Systems (ECoS). ECoS are a class of constructive neural networks that learn very quickly and that do not suffer from catastrophic forgetting. The website has overviews of several ECoS algorithms, a comprehensive listing of the ECoS literature, and also links to the ECoS Toolbox, which is a collection of Windows command-line tools that implement several ECoS algorithms.
Update: this website is now at http://ecos.watts.net.nz/
Update: this website is now at http://ecos.watts.net.nz/
Friday, May 21, 2010
Conference paper deadline extension: KDIR 2010
The deadline for the International Conference on Knowledge Discovery and Information Retrieval (KDIR) 2010 has been extended to 4th June 2010.
Tuesday, May 18, 2010
Conference paper extension: ICNC 2010
The deadline for the International Conference on Neural Computation (ICNC) 2010 has been extended to 31 May 2010.
Monday, May 17, 2010
International Neural Network Society - Australian Chapter
I'm a member of the INNS, the International Neural Networks Society, which is a good organisation to belong to if you're interested in neural networks. I'm in the process of setting up a regional chapter for Australia. If you are a member of the INNS and live in Australia, please contact me so I can add you to my mailing list for this chapter.
Wednesday, April 21, 2010
Conference paper deadline: KDIR 2010
The paper submission deadline for the International Conference on Knowledge Discovery and Information Retrieval (KDIR) 2010 is May 20, 2010. This conference will be held in Valencia, Spain, 25-28 October, 2010.
Subscribe to:
Posts (Atom)
Posts
