Monday, October 17, 2011
Paper submission deadline: ICML 2012
The deadline for submitting papers to the International Conference on Machine Learning (ICML) 2012 is 24 February 2012. This conference will be held in Edinburgh, Scotland, June 26 - July 1, 2012.
Friday, October 14, 2011
On Presentations
Some presenters are applauded because the audience enjoyed their presentation. Other presenters are applauded because they ended their presentation.
Know which one you are.
Know which one you are.
Call for papers: WIVACE 2012
The deadline for submitting papers to the Italian Workshop on Artificial Life, Evolution and Complexity (WIVACE) 2012 is 6 January 2012. This workshop will be held in Parma, Italy, 20-21 February, 2012.
Thursday, October 13, 2011
Paper submission deadline: EvoStar 2012
The deadline for submitting papers to the European Conference on Evolutionary Computation (EvoStar) 2012 is 30 November 2012. This conference will be held in Malaga, Spain, 11-13 April, 2012.
Wednesday, October 12, 2011
Call for papers: ICCCI 2012
The deadline for papers submitted to the 4th International Conference on Computational Collective Intelligence (ICCCI) 2012 is 15 April 2012. This conference will be held in Ho Chi Minh City, Vietnam, 28-30 November, 2012.
Tuesday, October 11, 2011
Open research problems with Evolving Connectionist Systems
I described Evolving Connectionist Systems (ECoS) in an earlier post. A couple of years ago, I published a review article (PDF preprint) where I described the state of the art of ECoS, and identified several open research problems. There hasn't been much progress made in solving these problems, so I'm going to briefly describe them here, and hopefully stimulate a bit more work in this area. Of course, I'm doing a bit of work in some of these, but as I have a real job to do, I don't get as much time to spend on these problems as I'd like.
1) Input significance. With other ANN, especially the venerable MLP, it is possible to get an indication of how important each input variable is to the model. These methods are based on an analysis of the magnitude of the connection weights attached to each input neuron. This method won't work with ECoS networks, however, because the connection weights represent points in space. That is, the magnitude of the weight for an input neuron connection has nothing to do with how important that input is.
2) Optimisation of ECoS networks. While ECoS algorithms are fast learning, they can grow to be quite large, which makes them expensive in terms of memory and computational load. Ideally, it would be possible to reduce their size without sacrificing their accuracy. That is, it would be ideal if we could somehow eliminate redundant information in the ECoS and only retain that which is necessary for maintaining accuracy. I investigated a couple of methods of doing this in my PhD, and a few other people have looked at it as well, but no one has yet cracked the problem in terms of coming up with an optimisation algorithm that will significantly reduce the size of a trained ECoS network without significantly reducing its accuracy. Also, the most effective optimisation methods in the published work use evolutionary algorithms like genetic algorithms or evolution strategies. These are so computationally intensive that the speed advantages of ECoS are lost. An ECoS optimisation algorithm would ideally be as fast, or nearly as fast, as the ECoS training algorithm. It may be that this is inherently impossible.
3) Non-triangular fuzzy membership functions in EFuNN. The Evolving Fuzzy Neural Network EFuNN has triangular fuzzy membership functions (MF) embedded in its structure. These are fast and efficient, but other MF types (such as Gaussian) may be more useful for other applications.
4) Learning in the MF of EFuNN. The fuzzy MF in EFuNN are fixed, that is, they are set once and do not change during the life of the EFuNN. This is in contrast to the open, adaptive nature of EFuNN itself. An extension of the EFuNN learning algorithm that would allow the MF to adapt as the rest of the network adapts, would be extremely useful for data mining applications. This algorithm would have to be as fast as the rest of the EFuNN learning algorithm, which may rule out backpropagation training of the MF, as is used in other fuzzy system optimisation.
Although ECoS networks are very useful algorithms, they could be made even more useful if the problems above were solved. I'm working on some of them, but I would love to see others working on them as well. Contact me if you are interested in collaborating.
1) Input significance. With other ANN, especially the venerable MLP, it is possible to get an indication of how important each input variable is to the model. These methods are based on an analysis of the magnitude of the connection weights attached to each input neuron. This method won't work with ECoS networks, however, because the connection weights represent points in space. That is, the magnitude of the weight for an input neuron connection has nothing to do with how important that input is.
2) Optimisation of ECoS networks. While ECoS algorithms are fast learning, they can grow to be quite large, which makes them expensive in terms of memory and computational load. Ideally, it would be possible to reduce their size without sacrificing their accuracy. That is, it would be ideal if we could somehow eliminate redundant information in the ECoS and only retain that which is necessary for maintaining accuracy. I investigated a couple of methods of doing this in my PhD, and a few other people have looked at it as well, but no one has yet cracked the problem in terms of coming up with an optimisation algorithm that will significantly reduce the size of a trained ECoS network without significantly reducing its accuracy. Also, the most effective optimisation methods in the published work use evolutionary algorithms like genetic algorithms or evolution strategies. These are so computationally intensive that the speed advantages of ECoS are lost. An ECoS optimisation algorithm would ideally be as fast, or nearly as fast, as the ECoS training algorithm. It may be that this is inherently impossible.
3) Non-triangular fuzzy membership functions in EFuNN. The Evolving Fuzzy Neural Network EFuNN has triangular fuzzy membership functions (MF) embedded in its structure. These are fast and efficient, but other MF types (such as Gaussian) may be more useful for other applications.
4) Learning in the MF of EFuNN. The fuzzy MF in EFuNN are fixed, that is, they are set once and do not change during the life of the EFuNN. This is in contrast to the open, adaptive nature of EFuNN itself. An extension of the EFuNN learning algorithm that would allow the MF to adapt as the rest of the network adapts, would be extremely useful for data mining applications. This algorithm would have to be as fast as the rest of the EFuNN learning algorithm, which may rule out backpropagation training of the MF, as is used in other fuzzy system optimisation.
Although ECoS networks are very useful algorithms, they could be made even more useful if the problems above were solved. I'm working on some of them, but I would love to see others working on them as well. Contact me if you are interested in collaborating.
Monday, October 10, 2011
Call for papers: IEEE SSCI 2013
The deadline for the IEEE Symposium Series in Computational Intelligence 2013 is 10 October 2012. This series of symposia will be held in Singapore 16-19 April 2013.
Thursday, October 6, 2011
The problem with academic journals 2
In this earlier post I linked to an article by George Monbiot that discussed the biggest problem with academic journals, which is the enormous expense of accessing journals or journal articles, given that the content and quality control are all provided for free.
Monbiot's original article touched off something of a storm in the academic web, with some echoing his sentiments, and others (some of whom, at least, were connected to the publishers) attacking him. The publishers themselves tried to justify their charges by writing a lot without saying very much (I find as I lurch remorselessly towards 40 that I have less and less tolerance for corporate weasel-wording). Still others discussed whether open access journals are feasible alternatives.
I serve on the editorial board of an open access journal, so I know that they can have a problem with legitimacy, or at least with being taken seriously. But open access journals are still fairly new, and it takes time for a journal to build up its article base, which in turn allows it to build up its citation rate, which in turn builds its impact factor, which is the most important, or at least the most widely known, measure of a journal's success, despite the problems with it.
From my own point of view, I review papers for open access journals with the same care as I review any other paper. As a working scientist and active author, if I can't find a copy of an article online, I won't cite it. It's the authors of the paper who are missing out then, it makes no difference to me whatsoever if they get cited or not.
It's interesting that an august institution like Princeton university, in an effort to promote open-access journals, has recently enacted a policy that forbids its staff from assigning copyright of articles to journal publishers. Let's hope that we see more top institutions doing the same thing: the sooner we break the stranglehold on top science held by the old publishers, the better for everyone.
Monbiot's original article touched off something of a storm in the academic web, with some echoing his sentiments, and others (some of whom, at least, were connected to the publishers) attacking him. The publishers themselves tried to justify their charges by writing a lot without saying very much (I find as I lurch remorselessly towards 40 that I have less and less tolerance for corporate weasel-wording). Still others discussed whether open access journals are feasible alternatives.
I serve on the editorial board of an open access journal, so I know that they can have a problem with legitimacy, or at least with being taken seriously. But open access journals are still fairly new, and it takes time for a journal to build up its article base, which in turn allows it to build up its citation rate, which in turn builds its impact factor, which is the most important, or at least the most widely known, measure of a journal's success, despite the problems with it.
From my own point of view, I review papers for open access journals with the same care as I review any other paper. As a working scientist and active author, if I can't find a copy of an article online, I won't cite it. It's the authors of the paper who are missing out then, it makes no difference to me whatsoever if they get cited or not.
It's interesting that an august institution like Princeton university, in an effort to promote open-access journals, has recently enacted a policy that forbids its staff from assigning copyright of articles to journal publishers. Let's hope that we see more top institutions doing the same thing: the sooner we break the stranglehold on top science held by the old publishers, the better for everyone.
Wednesday, October 5, 2011
Conference paper deadline: GECCO 2012
The deadline for submitting papers to the 2012 Genetic and Evolutionary Computation Conference (GECCO) is 13 January 2012. This conference will be held in Philadelphia 7-11 July, 2012.
Tuesday, October 4, 2011
Reminder: paper deadline for Collective Intelligence 2012
A reminder that 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, October 3, 2011
Reminder: paper submission deadline for EAIS 2012
A reminder that 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.
Friday, September 30, 2011
Reminder: paper submission deadline 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.
Thursday, September 29, 2011
Reminder: Paper submission deadline SAMI 2012
A reminder that 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.
Wednesday, September 28, 2011
Paper submission deadline: ISICA 2012
The deadline for papers submitted to the International Symposium on Intelligence Computing and Applications (ISICA) 2012 is 15 April 2012. This conference will be held in Wuhan, China, 27-28 October, 2012.
Tuesday, September 27, 2011
Paper submission deadline: IEEE CISDA 2012
The deadline for papers submitted to the IEEE Workshop on Computational Intelligence for Security and Defence Applications (IEEE CISDA) 2012 is 19 March 2012. This workshop will be held in Ottawa, Canada, 11-13 July 2012.
Monday, September 26, 2011
Reminder: paper submission deadline for IEEE-IS
A reminder that the deadline for submitting papers to the IEEE International Conference on Intelligent Systems (IEEE-IS) is 20 December 2011. This conference will be held in Sofia, Bulgaria, September 6-8, 2012.
Friday, September 23, 2011
Reminder: Paper deadline for IEEE CIFEr 2012
A reminder that 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.
Thursday, September 22, 2011
Reminder: Paper submission deadline for ICAISC 2012
A reminder that 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.
Wednesday, September 21, 2011
Reminder: Paper deadline FUZZ-IEEE 2012
A reminder that 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.
Reminder: Paper deadline CEC 2012
A reminder that 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.
Subscribe to:
Posts (Atom)
Posts
