Open source textbook - Chapter 2 outline

The outline of Chapter 2 of the open-source textbook "Intelligent Information Systems" is now available online. Chapter 2 is entitled "Simple and Linear Transformations" and is intended to be a brief overview of some of the data processing techniques that can be used to prepare data before it is modeled with computational intelligence techniques. My previous post about the outline of Chapter 1, "Introduction to Intelligent Information Systems", is here.

As always, you comments and suggestions are requested and valued.

Conference paper deadline: KES IIMSS 2013

The deadline for submitting papers to the 6th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS) 2013 is 6 January 2013. This conference will be held in Sesimbra, Portugal, 26 - 28 June, 2013.

Open source textbook - Chapter 1 outline

Following on from my post last week about the updated outline for my open-source textbook "Intelligent Information Systems", I've made the outline of Chapter 1 "Introduction to Intelligent Information Systems" available online.

As always, comments and suggestions are most welcome!

Reminder: conference paper deadline: KES-IDT 2013

A reminder that the deadline for submitting papers to the 5th International Conference on Intelligent Decision Technologies (KES-IDT) is 6 January 2013. This conference will be held in Sesimbra, Portugal, 26-28 June 2013.

Reminder: paper submission deadline for Fuzz-IEEE 2013

A reminder that the deadline for submitting papers to the IEEE Conference on Fuzzy Systems (Fuzz-IEEE) 2013 is 5 January, 2013. This conference will be held in Hyderabad, India, 7-10 July, 2013.

Important dates for IJCNN 2013

Some important dates for the International Joint Conference on Neural Networks (IJCNN) 2013. The following are all due by December 15, 2012:

• Tutorials proposals
• Workshop proposals
• Panel proposals
• Special sessions proposals

For more information, see the IJCNN website: www.ijcnn2013.org.

An experiment in open-source textbooks 2

In an earlier post, I described how I'm working on an open source textbook about Intelligent Information Systems.

While progress has been slower than I would have liked (mainly due to my relocating permanently to my native New Zealand), I have been able to digest the suggestions made in the comments on my previous post. As a result, I've made the second outline of this textbook available here.

I've also investigated several different licensing schemes, and it looks like I'll be going with one of the Creative Commons licenses. I'm looking at making the LaTeX source and PDF files freely available online, while retaining the print rights.

Any comments on the outline, or my licensing plan, will be gratefully received!

Reminder: paper submission deadline for EvoStar 2013

A reminder that the paper submission deadline for EvoStar 2013 is 1 November, 2012. This conference will be held in Vienna, Austria, 3-5 April, 2013.

The Problem with Academic Journals 7

The following quote was in an email I received from the editor of a certain prestigious general science journal:

"Your manuscript is now undergoing an initial screening to determine whether it will be sent for in-depth review. We will notify the corresponding author of our decision as soon as possible."

That really annoyed me. It annoyed me because it is not the job of the editor to screen submissions. Sure, it is appropriate for them to check that the paper is formatted correctly, that there aren't big sections of it missing, and that it fits the theme of the journal (which is not the case with general science journals like the journal this paper was submitted to). The kind of screening this editor is talking about it a kind of pre-peer review, where the editor is determining whether the paper is worthy of being considered by their august publication. It is, in fact, a rather extreme form of academic arrogance.

Having a paper rejected by peer review is one thing, but being rejected because one person doesn't think it's worthy enough? So many of my colleagues have had so many perfectly good papers rejected by editors without going to peer review. The purpose of peer review is to find errors in the science (and have no doubt about it, computational intelligence is a science). If there are no errors in the science - that is, there are no discernible errors in methodology or interpretation of results - then the paper should be published. Even a rejection is useful, as it allows the authors to improve their research. But editorial rejections eliminate even that, they make the entire process of submitting to that journal a waste of time.

As I've said many times before, the solution is to go to open access journals. Peer review will help catch the errors, and the people reading the papers (and there will be a lot more of them reading open access papers than subscription-only papers) will find the errors the peer reviewers missed. But arrogant editors from expensive subscription-only journals will soon find themselves presiding over a shrinking author base.

IEEE Transactions on Autonomous Mental Development: Volume 4, Issue 3, 2012

1. Editorial: Impact Factor and Outstanding Paper Awards
Zhang, Z.
Page(s): 189
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6298016

2. Guest Editorial: Biologically Inspired Human–Robot Interactions—Developing More Natural Ways to Communicate with our Machines
Harris, C.; Krichmar, L.; Siegelmann, T.; Wagatsuma, H
Page(s): 190 - 191
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6298018

3. Long Summer Days: Grounded Learning of Words for the Uneven Cycles of Real World Events
Heath, S.; Schulz, R.; Ball, D.; Wiles, J.
Page(s): 192 - 203
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6236014

4. Learning Through Imitation: a Biological Approach to Robotics
Chersi, F.
Page(s): 204 - 214
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6203559

5. Context-Based Bayesian Intent Recognition
Kelley, R.; Tavakkoli, A.; King, C.; Ambardekar, A.; Nicolescu, M.; Nicolescu, M.
Page(s): 215 - 225
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6276240

6. Reciprocity and Retaliation in Social Games With Adaptive Agents
Asher, D. E.; Zaldivar, A.; Barton, B.; Brewer, A. A.; Krichmar, J. L.
Page(s): 226 - 238
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6212318

7. Towards a Platform-Independent Cooperative Human Robot Interaction System: III An Architecture for Learning and Executing Actions and Shared Plans
Lallee, S.; Pattacini, U.; Lemaignan, S.; Lenz, A.; Melhuish, C.; Natale, L.; Skachek, S.; Hamann, K.; Steinwender, J.; Sisbot, E. A.; Metta, G.; Guitton, J.; Alami, R.; Warnier, M.; Pipe, T.; Warneken, F.; Dominey, P. F.
Page(s): 239 - 253
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6204326

IEEE Transactions on Computational Intelligence and AI in Games: Volume 4, Issue 3, 2012

1. Guest Editorial: Special Issue on Computational Aesthetics in Games
Browne, C.; Yannakakis, G. N.; Colton, S.
Page(s): 149 - 151
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6299016

2. Unsupervised Modeling of Player Style With LDA
Gow, J.; Baumgarten, R.; Cairns, P.; Colton, S.; Miller, P.
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6269992

3. Beyond Skill Rating: Advanced Matchmaking in Ghost Recon Online
Delalleau, O.; Contal, E.; Thibodeau-Laufer, E.; Ferrari, R. C.; Bengio, Y.; Zhang, F.
Page(s): 167 - 177
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6156756

4. Evaluating the Aesthetics of Endgame Studies: A Computational Model of Human Aesthetic Perception
Iqbal, A.; van der Heijden, H.; Guid, M.; Makhmali, A.
Page(s): 178 - 191
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6177652

5. Experience-Driven Procedural Music Generation for Games
Plans, D.; Morelli, D.
Page(s): 192 - 198
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6266725

6. Continuous Recognition of Player's Affective Body Expression as Dynamic Quality of Aesthetic Experience
Savva, N.; Scarinzi, A.; Bianchi-Berthouze, N.
Page(s): 199 - 212
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6212341

7. Adapting Models of Visual Aesthetics for Personalized Content Creation
Liapis, A.; Yannakakis, G. N.; Togelius, J.
Page(s): 213 - 228
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6185648

8. Elegance in Game Design
Browne, C.
Page(s): 229 - 240
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6194295

Reminder: paper submission deadline for ICAISC 2013

A reminder that the deadline for submitting papers to the International Conference on Artificial Intelligence and Soft Computing (ICAISC) 2013 is November 20, 2012. This conference will be held in Zakopane, Poland, June 9-13, 2013.

On Being a Post-doc

After completing a PhD, most people who wish to stay in academia end up doing one or more post-doctoral positions. Experience as a post-doc is a prerequisite for a career in scientific research, as it is during your post-doc career that you get exposure to ideas and techniques outside of your PhD, and work with a wider range of people than you did during your PhD. The chances of going into a permanent academic position, without doing at least one post-doc, are very slim (most people who manage to do this tend to wind up in the same department they did their PhD in). I've done three post-docs, at Lincoln University in New Zealand, at the University of Sydney, and the University of Adelaide, both of which are in Australia.

So, what's it like being a post-doctoral fellow?

Basically, it sucks. Most post-docs are for two or three years. This term is fixed as the position is usually tied to a particular research grant, which is itself of fixed duration. This means that even if you do extremely well in your research, there is no guarantee of further employment after the contract ends. This means that as a post-doc, you will probably be changing jobs and cities every two years. If you're young and single, that's not entirely a bad thing: travelling and living in different places broadens your mind, can build a wide network of friendships and helps you appreciate different ways of life. Things get harder if you are a couple, as your partner also needs to find work in your new home. If you have even one child, it's a nightmare: you need to find a new school, your child faces the awful wrench of leaving their friends behind, if they're in after-school activities they need to be organised all over again, and if they have even minor health issues, finding adequate care for them can be very challenging. The stress that this can place on your relationship is enormous. In short, being a post-doc is a young (single) person's game.

If your post-doc is tied to a grant, then you will be working on someone else's project. In other words, you'll be working on something that is interesting to someone else (the grant holder). This also means that the outputs you produce (that is, papers) will be of benefit primarily to the grant holder rather than you.

While you should concentrate on doing the work you are paid to do, if you want to move up the academic ladder, then you also need to demonstrate the ability to do independent research. So, in addition to working a full-time job, you're also working part-time on your own research programme.

On top of the above are the dangers of any workplace: while most post-doc supervisors are good and kind people, they get their positions by being good researchers (or occasionally good politicians), not good managers. In the worst case, you might end up working for a narcissistic sociopath. Doing a post-doc with the wrong supervisor (or supervisors) can make your life a living hell. Sociopaths can be pretty hard to spot, too.

My experience is that it can take six months or more to find a new position, which means that shortly after starting a post-doc, you need to start looking for another. If your career is a chess game, then you need to start getting your pieces into place sooner rather than later.

To sum up, being a post-doctoral fellow means a semi-itinerant life of uncertainty and upheaval, serving the research needs of others, while also planning a future career that might not happen.

Was it all worth it for me? While there are many things I would do differently if I had the chance to do it all again, I don't want to live my life in regret: the things in my life, the good and the bad, the joy and the hurt, have all made me the person I am. But I do regret the hurt it has caused my family. Being a post-doc is hard on everyone if you have a family. It's not all bad news, though, and in a future post I'll be discussing ways in which you can make your post-doc career successful.

IEEE Transactions on Neural Networks and Learning Systems: Volume 23, Issue 10, October 2012

1. Title: Silicon-Based Dynamic Synapse With Depressing Response
Authors: Thomas Dowrick; Steve Hall; Liam J. McDaid
Page(s): 1513 - 1525
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6287129


2. Title: Self-Organizing Spiking Neural Model for Learning Fault-Tolerant Spatio-Motor Transformations
Authors: Narayan Srinivasa; Youngkwan Cho
Page(s): 1526 - 1538
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6248739


3. Title: Learning From ISS-Modular Adaptive NN Control of Nonlinear Strict-Feedback Systems
Authors: Cong Wang; Min Wang; Tengfei Liu; David. J. Hill
Page(s): 1539 - 1550
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6248726


4. Title: Synchronization Error Estimation and Controller Design for Delayed Lur'e Systems With Parameter Mismatches
Authors: Wangli He; Feng Qian; Qing-Long Han; Jinde Cao
Page(s): 1551 - 1563
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6248725&tag=1


5. Title: Reproducing Kernel Hilbert Spaces With Odd Kernels in Price Prediction
Authors: Miloš Krejník; Anton Tyutin
Page(s): 1564 - 1573
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6253266


6. Title: Neural Modeling of Episodic Memory: Encoding, Retrieval, and Forgetting
Authors: Wenwen Wang; Budhitama Subagdja; Ah-Hwee Tan; Janusz A. Starzyk
Page(s): 1574 - 1586
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6261552


7. Title: A Discrimination Analysis for Unsupervised Feature Selection via Optic Diffraction Principle
Authors: Praisan Padungweang; Chidchanok Lursinsap; Khamron Sunat
Page(s): 1587 - 1600
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6263306


8. Title: Nonnegative Blind Source Separation by Sparse Component Analysis Based on Determinant Measure
Authors: Zuyuan Yang; Yong Xiang; Shengli Xie; Shuxue Ding; Yue Rong
Page(s): 1601 - 1610
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6263307


9. Title: Multiclass Feature Selection With Kernel Gram-Matrix-Based Criteria
Authors: Mathieu Ramona; Gaël Richard; Bertrand David
Page(s): 1611 - 1623
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6264104


10. Title: Efficient Online Subspace Learning With an Indefinite Kernel for Visual Tracking and Recognition
Authors: Stephan Liwicki; Stefanos Zafeiriou; Georgios Tzimiropoulos; Maja Pantic
Page(s): 1624 - 1636
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6269106


11. Title: Feedback Control by Online Learning an Inverse Model
Authors: Tim Waegeman; Francis wyffels; Benjamin Schrauwen
Page(s): 1637 - 1648
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6269107


12. Title: Symbolic Representation of Recurrent Neural Network Dynamics
Authors: Thuan Q. Huynh; James A. Reggia
Page(s): 1649 - 1658
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6269105


13. Title: Inphase and Antiphase Synchronization in a Delay-Coupled System With Applications to a Delay-Coupled FitzHugh–Nagumo System
Authors: Yongli Song; Jian Xu
Page(s): 1659 - 1670
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6269931


14. Title: Simple and Fast Calculation of the Second-Order Gradients for Globalized Dual Heuristic Dynamic Programming in Neural Networks
Authors: Michael Fairbank; Eduardo Alonso; Danil Prokhorov
Page(s): 1671 - 1676
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6239600

Reminder: paper submission deadline for IEEE-SSCI 2013

A reminder that 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.

Reminder: paper submission deadline for ICANNGA 2013

A reminder that the paper submission deadline for the International Conference on Adaptive and Natural Computing Algorithms (ICANNGA) 2013 is 8 October, 2013. This conference will be held in Lausanne, Switzerland, April 4-6, 2013.

Deadline Extension - IEEE CIS Facebook Photo Contest

This is cross-posted from the IEEE Computational Intelligence Society blog.

---

Due to many requests, we have decided to extend the deadline of the Facebook Photo Contest to September 30, 2012.

There will be three winners, each of them will get a free CIS membership for 2013. The best out of the three winners will get a FREE IPAD2. More information can be found at http://www.tinyurl.com/cisfb2012. If you have any questions, please send a email to cis.socialmedia@gmail.com.  

Guest post: Write Right First Time with Brown's Eight Questions

This is a guest post by Stephen G. Matthews. Stephen is a PhD student in the Centre for Computational Intelligence at De Montfort University, UK.

---

Write Right First Time with Brown's Eight Questions

I will share a method that I have found to be really useful. It's short, simple and incredibly effective: Brown's Eight Questions.

Robert Brown introduced Brown's Eight Questions (Brown, 1994/95) as part of an action learning set for improving writing. An action learning set is a group of people (ideally 5) who meet up to discuss common problems and solutions. Brown suggests applying this to writing for publication. An action learning set meets up and each member reviews each other's manuscripts face to face. I will focus on Brown's Eight Questions, but an action learning set for writing is well worth reading about in Brown's article.

So what is Brown's Eight Questions? Well, it is a set of eight questions designed to make an author think about writing before actually writing a first draft. Brown's idea, which was motivated by his experiences as a writer, reviewer and editor, comes from his observation that writers often focus on correcting a manuscript once it is written, rather than planning the manuscript before writing.

Brown’s Eight Questions

1. Who are the intended readers? - list 3 to 5 of them by name;
2. What did you do? (limit - 50 words)
3. Why did you do it? (limit - 50 words)
4. What happened? (limit - 50 words)
5. What do the results mean in theory? (limit - 50 words)
6. What do the results mean in practice? (limit - 50 words)
7. What is the key benefit for your readers? (limit - 25 words)
8. What remains unresolved? (no word limit)

As you can see these are simple questions and the word limit ensures answers are succinct. Brown's Eight Questions can help authors to gain clarity about their manuscript and also support the reader's understanding.

Brown's Eight Questions helps me to structure my thoughts, arguments and the message of a manuscript. It really is a useful method that can be applied to any form of writing such as journal articles, theses and reports. If you have not used it then give it a go!

Brown, Robert (1994/95) “Write Right First Time”, Literati Newsline Special Issue: 1-8. (Available from http://web.archive.org/web/19971014014626/http://www.mcb.co.uk/literati/write.htm)

Evolving Systems Volume 3 Issue 3

1. A dynamic split-and-merge approach for evolving cluster models
Edwin Lughofer
http://springer.r.delivery.net/r/r?2.1.Ee.2Tp.1jfPPN.C3agc4..H.WsNM.3vVy.bW89MQ%5f%5fDGVOFSD0

2. Online variational learning of finite Dirichlet mixture models
Wentao Fan and Nizar Bouguila
http://springer.r.delivery.net/r/r?2.1.Ee.2Tp.1jfPPN.C3agc4..H.WsNS.3vVy.bW89MQ%5f%5fDHJKFSJ0

3. Adaptive complex event processing for harmful situation detection
Jean-René Coffi, Christophe Marsala and Nicolas Museux
http://springer.r.delivery.net/r/r?2.1.Ee.2Tp.1jfPPN.C3agc4..H.WsNY.3vVy.bW89MQ%5f%5fDHdGFSP0

4. Sliding mode incremental learning algorithm for interval type-2 Takagi–Sugeno–Kang fuzzy neural networks
Sevil Ahmed, Nikola Shakev, Andon Topalov, Kostadin Shiev and Okyay Kaynak
http://springer.r.delivery.net/r/r?2.1.Ee.2Tp.1jfPPN.C3agc4..H.WsNe.3vVy.bW89MQ%5f%5fDJEeFSb0

5. Negotiating in dynamic environments: time-efficient automated negotiations by means of combinatorial auctions
Fabian Lang and Andreas Fink
http://springer.r.delivery.net/r/r?2.1.Ee.2Tp.1jfPPN.C3agc4..H.WsNk.3vVy.bW89MQ%5f%5fDJYaFTB0

Posting Hiatus

Next week my family and I will be moving away from Adelaide and leaving Australia permanently. We are moving so that I can take up a new, permanent, academic position. Since this move will involve a fair amount of chaos and interrupted Internet access (at least until we find a house and get the Internet connected again), posting to this blog will be quite sporadic.

IEEE Transactions on Neural Networks and Learning Systems: Volume 23, Issue 9, September 2012

1. Adaptive Pinning Control of Deteriorated Nonlinear Coupling Networks With Circuit Realization
Xiao-Zheng Jin; Guang-Hong Yang; Wei-Wei Che
Page(s): 1345 - 1355
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6222060

2. Approximate Solutions to Ordinary Differential Equations Using Least Squares Support Vector Machines
Siamak Mehrkanoon; Tillmann Falck; Johan A. K. Suykens
Page(s): 1356 - 1367
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6224185

3. Exponential Synchronization of Neural Networks With Discrete and Distributed Delays Under Time-Varying Sampling
Zheng-Guang Wu; Peng Shi; Hongye Su; Jian Chu
Page(s): 1368 - 1376
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6227362

4. Convergence and Rate Analysis of Neural Networks for Sparse Approximation
Aurèle Balavoine; Justin Romberg; Christopher J. Rozell
Page(s): 1377 - 1389
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6227360

5. In-Sample and Out-of-Sample Model Selection and Error Estimation for Support Vector Machines
Davide Anguita; Alessandro Ghio; Luca Oneto; Sandro Ridella
Page(s): 1390 - 1406
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6228541

6. Robust Exponential Stability of Uncertain Stochastic Neural Networks With Distributed Delays and Reaction-Diffusions
Jianping Zhou; Shengyuan Xu; Baoyong Zhang; Yun Zou; Hao Shen
Page(s): 1407 - 1416
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6228542

7. Online Kernel-Based Learning for Task-Space Tracking Robot Control
Duy Nguyen-Tuong; Jan Peters
Page(s): 1417 - 1425
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6230657

8. Memristor Bridge Synapse-Based Neural Network and Its Learning
Shyam Prasad Adhikari; Changju Yang; Hyongsuk Kim; Leon O. Chua
Page(s): 1426 - 1435
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6232461

9. Efficient Sparse Modeling With Automatic Feature Grouping
Leon Wenliang Zhong; James T. Kwok
Page(s): 1436 - 1447
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6238378

10. Hierarchical Approach for Multiscale Support Vector Regression
Francesco Bellocchio; Stefano Ferrari; Vincenzo Piuri; Nunzio Alberto Borghese
Page(s): 1448 - 1460
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6238377

11. Discretized-Vapnik-Chervonenkis Dimension for Analyzing Complexity of Real Function Classes
Chao Zhang; Wei Bian; Dacheng Tao; Weisi Lin
Page(s): 1461 - 1472
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6239601

12. Limit Set Dichotomy and Multistability for a Class of Cooperative Neural Networks With Delays
Mauro Di Marco; Mauro Forti; Massimo Grazzini; Luca Pancioni
Page(s): 1473 - 1485
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6241435

13. Adaptive Visual and Auditory Map Alignment in Barn Owl Superior Colliculus and Its Neuromorphic Implementation
Juan Huo; Alan Murray; Dongqing Wei
Page(s): 1486 - 1497
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6255791

14. Bidirectional Extreme Learning Machine for Regression Problem and Its Learning Effectiveness
Yimin Yang; Yaonan Wang; Xiaofang Yuan
Page(s): 1498 - 1505
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6222007

15. Enhancing Weak Signal Transmission Through a Feedforward Network
Xiaoming Liang; Liang Zhao; Zonghua Liu
Page(s): 1506 - 1512
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6227359

ECoS toolbox API?

Is anyone interested in an ECoS DLL / API? I'm thinking of wrapping the functionality in the command-line ECoS Toolbox up in a DLL and providing an API so that people could include EFuNN and SECoS in their own programs. Is this a worthwhile use of my time? Would anyone use it?

Reminder: paper submission deadline for CEC 2013

A reminder that the deadline for submitting papers to the IEEE Congress on Evolutionary Computation (CEC) 2013 is February 15, 2013. This conference will be held in Cancun, Mexico, June 20-23, 2013.

Identifying bats with ANN

An interesting paper has just come out in the Journal of Applied Ecology, which describes how ANN were used to identify thirty-four European species of bats based on their echolocation calls. This is a challenging problem, because the calls within any bat species can vary quite a lot, depending on what the bat is doing. For example, the calls that a bat uses while hunting are different to the calls that a bat uses while commuting to a hunting ground. The work described in this paper has several good features.

Firstly, they used a hierarchy of MLP ensembles to identify the species. First a level of MLP identified the geographic region (out of six) that the bat came from. Then a second level was used to identify the genus (out of seven) of the bat. Finally, an ensemble of species-specific MLP identified the species itself.

Secondly, they used a large data set to train the MLP, and performed a thorough data analysis to identify the significant features. Rather than just cramming every acoustic feature through the MLP and hoping for the best, they only used the most significant twenty-four.

Finally, they incorporated the classifiers into software called iBatsID that is freely available for anyone to use.

The authors reported a range of classification accuracies across the species, from a high of 100% to a low of 56.5%. They say that "This is almost certainly the results of our eANN [ensemble ANN] dealing with many more species". I think they're wrong when they say that, because the point of using ensembles is that the individual members of the ensemble can be highly specialised for a particular class. I suspect that the problem may be that the features they selected were not as useful for classifying the poorly-recognised species: rather than using the same twenty-four parameters for all thirty-four species, they might have gotten better results by selecting acoustic parameters for each species. Also, from the diagram (Figure 3 in the paper) it looks like they used the outputs of the regional and genus networks only to decide which groups of species MLP to use. An alternative would have been to use the output of the regional and genus MLP as input features for the following levels (similar to my approach in this paper), which would have added some more information into the classification process and probably boosted accuracy.

A final problem with this paper is that they have excluded a lot of the technical details about constructing and training the ANN, and about exactly how the different levels in the hierarchy interacted. This is probably because it is an ecology paper, not an ANN paper.

Overall, it's an interesting application, and I'm looking forward to seeing more work done on this problem in the future.

The problem with academic journals 6

In my previous posts on academic journals (see here, here, here, here, here, and here) I've discussed the major problem with academic journals in the context of the huge cost of accessing the content that the journals receive for free, as well as the importance of open-access journals. This post is concerned with another problem that is becoming apparent with journals: the declining acceptance rate for papers submitted to journals, in attempts to foster an image of exclusivity and quality.

A recent editorial by David Wardle describes a quantitative analysis he performed that compared the acceptance rates of four top-ranked ecological journals with the large open-access journal PLoS One, along with the citation rate of papers published in each. What he found was that the four traditional journals accepted less than 20% of the paper submitted to them, while PLoS One accepted around 69%. However, papers that are published in PLoS One are cited more than papers published in one of the traditional journals. His argument was that the traditional journals rejected papers that were of good scientific quality (that is, they described good work) but were not "worthy" of publication in such "august" journals, with the editors using the excuse that limited page space meant that there wasn't room to print the papers, even though they were quite good. He then goes on to explain that this exclusivity was motivated by a desire to increase the perception of quality of the journals. That is, the editors are trying to foster the impression that the journals must be really good, because they're really picky about which papers they publish.

But, the ultimate measure of the quality of a paper is how often it is cited, as that reflects how useful it is to other scientists, and papers published in the less-exclusive open-access journals are cited more. Thus, the concept that journals with low acceptance rates publish better papers is fatally flawed: these journals are rejecting papers that are scientifically sound and are useful to other scientists.

This leads me to think that the only reason the top journals are the top journals are because people think they are. If someone wants an authoritative citation to back up a statement they make in a paper, they will cite a paper in Nature or Science if they can, because these are the top journals (this doesn't happen much in computational intelligence, because very few papers in this field are published in Nature or Science). But the conclusion of Wardle's study is that acceptance rate is not a reliable metric of the quality of a journal. If anything, it is a measure of the snobbery of a journal.

The purpose of peer review (and of reviewers) is as a crap-filter for papers, to keep work that is incorrectly done or poorly presented from entering the literature. But with exclusive journals, the peer reviewers seem to be spending more time deciding which papers are significant enough to be published in the journal, rather than trying to identify flaws in the work. The whole thing reminds me of the reason the great physicist Richard Feynman quit the US National Academy of Science: because they spent most of their time deciding who was "worthy" of joining the Academy.

Not so long ago, we had to consider the quality of journals because it wasn't feasible to track the impact of a single paper. Now, with tools like Google Scholar, we can track the citation histories of individual papers. In short, the journal in which a paper is published is no longer that important: the usefulness, the contribution of the paper is what is important. By the same token, the quality of an academic is not measured by which institution they work for, but by their contributions. Unfortunately, the bean-counters who make the hiring and promotion decisions, and who make decisions on who gets competitive research funding, haven't grasped this concept yet.

Exclusive journals do not make a good contribution to science, as they keep too much useful material out of the public eye for too long: peer-reviewed open-access journals, with their more liberal acceptance rates, are more important then ever in this situation.

Final reminder: IEEE CIS Facebook Photo Competition

The IEEE Computational Intelligence Society are running a photo competition on Facebook. Go to http://www.watts.net.nz/CIS/contests/photo/2012/ or see the flyer below for further details.

The deadline is three weeks away!

Reminder: paper submission deadline for IJCNN 2013

A reminder that the deadline for submitting papers to the IEEE International Joint Conference on Neural Networks (IJCNN) 2013 is February 1, 2013. This conference will be held in Dallas, Texas, August 4-9, 2013.

Reminder: paper submission deadline for EvoStar 2013

A reminder that the paper submission deadline for EvoStar 2013 is 1 November, 2012. This conference will be held in Vienna, Austria, 3-5 April, 2013.

IEEE Transactions on Autonomous Mental Development: Volume 4, Issue 2, 2012

1. The “Interaction Engine”: A Common Pragmatic Competence Across Linguistic and Nonlinguistic Interactions
Pezzulo, G.
Page(s): 105 - 123
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6006515

2. Interactive Learning in Continuous Multimodal Space: A Bayesian Approach to Action-Based Soft Partitioning and Learning
Firouzi, H.; Ahmadabadi, M.N.; Araabi, B.N.; Amizadeh, S.; Mirian, M.S.; Siegwart, R.
Page(s): 124 - 138
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6032073

3. Tool–Body Assimilation of Humanoid Robot Using a Neurodynamical System
Nishide, S.; Tani, J.; Takahashi, T.; Okuno, H.G.; Ogata, T.
Page(s): 139 - 149
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6095595

4. Are Robots Appropriate for Troublesome and Communicative Tasks in a City Environment?
Hayashi, K.; Shiomi, M.; Kanda, T.; Hagita, N.
Page(s): 150 - 160
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6111246

5. Brain-Like Emergent Spatial Processing
Juyang Weng; Luciw, M.
Page(s): 161 - 185
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6095596

IEEE Transactions on Computational Intelligence and AI in Games: Volume 4, Issue 2, 2012

1. N-Grams and the Last-Good-Reply Policy Applied in General Game Playing
Tak, M.J.W.; Winands, M.H.M.; Bjornsson, Y.
Page(s): 73 - 83
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6203383

2. A Discrete Evolutionary Model for Chess Players' Ratings
Fenner, T.; Levene, M.; Loizou, G.
Page(s): 84 - 93
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6168229

3. Evolving Multimodal Networks for Multitask Games
Schrum, J.; Miikkulainen, R.
Page(s): 94 - 111
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6179519

4. Bitwise-Parallel Reduction for Connection Tests
Browne, C.; Tavener, S.
Page(s): 112 - 119
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6185647

5. Information Set Monte Carlo Tree Search
Cowling, P.I.; Powley, E.J.; Whitehouse, D.
Page(s): 120 - 143
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6203567

6. Benchmarks for Grid-Based Pathfinding
Sturtevant, N.R.
Page(s): 144 - 148
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6194296

IEEE Transactions on Evolutionary Computation: Volume 16, Issue 4, 2012

1. Solving Multicommodity Capacitated Network Design Problems Using Multiobjective Evolutionary Algorithms
Kleeman, M. P.; Seibert, B. A.; Lamont, G. B.; Hopkinson, K. M.; Graham, S. R.
Page(s): 449 - 471
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6151105


2. An Integrated Neuroevolutionary Approach to Reactive Control and High-Level Strategy
Kohl, N.; Miikkulainen, R.
Page(s): 472 - 488
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6151106


3. A Process Algebra Genetic Algorithm
Karaman, S.; Shima, T.; Frazzoli, E.
Page(s): 489 - 503
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6045330


4. Using the Averaged Hausdorff Distance as a Performance Measure in Evolutionary Multiobjective Optimization
Schutze, O.; Esquivel, X.; Lara, A.; Coello, C. A. C.
Page(s): 504 - 522
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6151115


5. Promoting Creative Design in Interactive Evolutionary Computation
Kowaliw, T.; Dorin, A.; McCormack, J.
Page(s): 523 - 536
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6151108


6. Effects of Iterated Interactions in Multiplayer Spatial Evolutionary Games
Chiong, R.; Kirley, M.
Page(s): 537 - 555
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6151098


7. A General Framework of Multipopulation Methods With Clustering in Undetectable Dynamic Environments
Li, C.; Yang, S.
Page(s): 556 - 577
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6151109


8. On the Design of Constraint Covariance Matrix Self-Adaptation Evolution Strategies Including a Cardinality Constraint
Beyer, H.-G.; Finck, S.
Page(s): 578 - 596
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6151095

IEEE Transactions on Fuzzy Systems: Volume 20, Issue 4, 2012

1. Finite-Time $H_{infty}$ Fuzzy Control of Nonlinear Jump Systems With Time Delays Via Dynamic Observer-Based State Feedback
He, S.; Liu, F.
Page(s): 605 - 614
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6094200

2. A Practical Approach to R&D Portfolio Selection Using the Fuzzy Pay-Off Method
Hassanzadeh, F.; Collan, M.; Modarres, M.
Page(s): 615 - 622
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6109284

3. Fuzzy Hardware: A Retrospective and Analysis
Zavala, A. H.; Nieto, O. C.
Page(s): 623 - 635
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6111466

4. On Robust Fuzzy Rough Set Models
Hu, Q.; Zhang, L.; An, S.; Zhang, D.; Yu, D.
Page(s): 636 - 651
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6111464

5. Fault-Tolerant Control for T–S Fuzzy Systems With Application to Near-Space Hypersonic Vehicle With Actuator Faults
Shen, Q.; Jiang, B.; Cocquempot, V.
Page(s): 652 - 665
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6111465

6. Constrained Fuzzy Hierarchical Analysis for Portfolio Selection Under Higher Moments
Nguyen, T. T.; Gordon-Brown, L.
Page(s): 666 - 682
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6112209

7. An Integrated Mechanism for Feature Selection and Fuzzy Rule Extraction for Classification
Chen, Y-.C.; Pal, N. R.; Chung, I-.F.
Page(s): 683 - 698
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6112676

8. Generalizing the Decentralized Control of Fuzzy Discrete Event Systems
Jayasiri, A.; Mann, G. K. I.; Gosine, R. G.
Page(s): 699 - 714
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6112712

9. Participatory Learning of Propositional Knowledge
Yager, R. R.
Page(s): 715 - 727
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6119214

10. The $K$-Means-Type Algorithms Versus Imbalanced Data Distributions
Liang, J.; Bai, L.; Dang, C.; Cao, F.
Page(s): 728 - 745
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6121900

11. Stress Monitoring Based on Stochastic Fuzzy Analysis of Heartbeat Intervals
Kumar, M.; Neubert, S.; Behrendt, S.; Rieger, A.; Weippert, M.; Stoll, N.; Thurow, K.; Stoll, R.
Page(s): 746 - 759
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6127913

12. Fuzzy Preferences in the Graph Model for Conflict Resolution
Bashar, M. A.; Kilgour, D. M.; Hipel, K. W.
Page(s): 760 - 770
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6127912

13. Observer-Based Adaptive Fuzzy Backstepping Output Feedback Control of Uncertain MIMO Pure-Feedback Nonlinear Systems
Tong, S. C.; Li, Y. M.; Shi, P.
Page(s): 771 - 785
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6126023

14. On the Use of a Fuzzy Object-Relational Database for Flexible Retrieval of Medical Images
Medina, J. M.; Jaime-Castillo, S.; Barranco, C. D.; Campana, J. R.
Page(s): 786 - 803
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6208854

Reminder: paper submission deadline for AROB 2013

A reminder that the deadline for submitting papers to the 18th International Symposium on Artificial Life and Robotics (AROB) 2013 is 1 September, 2012. This symposium will be held in Daejeon, Korea, January 30 - February 1st, 2013.

IEEE Transactions on Neural Networks and Learning Systems; Volume 23, Issue 8, August 2012

1. Title: Twenty Years of Mixture of Experts
Authors: Seniha Esen Yuksel; Joseph N. Wilson; Paul D. Gader
Page(s): 1177 - 1193
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6215056

2. Title: Constrained Empirical Risk Minimization Framework for Distance Metric Learning
Authors: Wei Bian; Dacheng Tao
Page(s): 1194 - 1205
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6203595

3. Title: Scale-Invariant Amplitude Spectrum Modulation for Visual Saliency Detection
Authors: Dongyue Chen; Hao Chu
Page(s): 1206 - 1214
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6212362

4. Title: Relaxed Fault-Tolerant Hardware Implementation of Neural Networks in the Presence of Multiple Transient Errors
Authors: Hamid Reza Mahdiani; Sied Mehdi Fakhraie; Caro Lucas
Page(s): 1215 - 1228
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6213557

5. Title: Mapping Dynamic Bayesian Networks to $alpha$-Shapes: Application to Human Faces Identification Across Ages
Authors: Djamel Bouchaffra
Page(s): 1229 - 1241
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6215055

6. Title: Predictive Approach for User Long-Term Needs in Content-Based Image Suggestion
Authors: Sabri Boutemedjet; Djemel Ziou
Page(s): 1242 - 1253
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6218198

7. Title: SOMKE: Kernel Density Estimation Over Data Streams by Sequences of Self-Organizing Maps
Authors: Yuan Cao; Haibo He; Hong Man
Page(s): 1254 - 1268
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6218200

8. Title: Reinforced Two-Step-Ahead Weight Adjustment Technique for Online Training of Recurrent Neural Networks
Authors: Li-Chiu Chang; Pin-An Chen; Fi-John Chang
Page(s): 1269 - 1278
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6218199

9. Title: Spatial Gaussian Process Regression With Mobile Sensor Networks
Authors: Dongbing Gu; Huosheng Hu
Page(s): 1279 - 1290
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6218781

10. Title: Adaptive Data Embedding Framework for Multiclass Classification
Authors: Tingting Mu; Jianmin Jiang; Yan Wang; John Y. Goulermas
Page(s): 1291 - 1303
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6220302

11. Title: Study on the Impact of Partition-Induced Dataset Shift on $k$-Fold Cross-Validation
Authors: Jose García Moreno-Torres; José A. Sáez; Francisco Herrera
Page(s): 1304 - 1312
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6226477

12. Title: Kernel Recursive Least-Squares Tracker for Time-Varying Regression
Authors: Steven Van Vaerenbergh; Miguel Lázaro-Gredilla; Ignacio Santamaría
Page(s): 1313 - 1326
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6227361

13. Title: Discrete-Time Neural Inverse Optimal Control for Nonlinear Systems via Passivation
Authors: Fernando Ornelas-Tellez; Edgar N. Sanchez; Alexander G. Loukianov
Page(s): 1327 - 1339
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6238379

14. Title: Equilibria of Perceptrons for Simple Contingency Problems
Authors: Michael R. W. Dawson; Brian Dupuis
Page(s): 1340- 1344
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6213123

Fraud in science

Ars Technica has a slightly tongue-in-cheek article on how to commit scientific fraud and get away with it. The article discusses eight points:

1. Fake data nobody ever expects to see
2. Work with many collaborators
3. Tell people what they already know
4. Don't do research anyone cares about
5. Don't publish in journals focused on your field
6. Distribute responsibility
7. Don't plagiarize
8. Don't duplicate images

It seems to me that, unfortunately, computational intelligence (CI) is more susceptible to many of these methods than many other fields. I sometimes joke that I am fortunate to work in a field where I can perform solid research by making stuff up as I go along, by which I mean that developing algorithms or techniques is often a more creative process than, for example, research in biology or physics. But think about how many CI papers you've seen that don't make the data available (point 1), or even describe its statistical parameters?

A long list of co-authors is not as common in CI (point 2) as it is in other fields, but I have seen many, many papers that are going over the same topic as has been covered many times before (point 3). Also, many, many papers cover minimal, slightly incremental "improvements" to existing algorithms that are of little true interest to most other researchers (point 4).

While one of the great joys of working in computational intelligence lies in the broad range of applications the field can be applied to, it does provide more opportunity to publish in journals that specialise is other fields (point 5).


The remaining three points (6-8) are more concerned with how not to get caught, or rather, how not to draw attention to yourself while committing fraud.

Fraud is always a problem, and I don't think that it is any less common in CI than in any other field. A greater emphasis on the use of statistics in CI papers would help guard against fraud (see my posts here and here about increasing the statistical basis of CI papers). But apart from that, we still depend on the honesty and integrity of the authors.

Reminder: IEEE CIS Facebook Photo Competition

The IEEE Computational Intelligence Society are running a photo competition on Facebook. See the flyer below to find out how to enter.

More on open access journals

Continuing my series of posts on open access journals (see here and here), this article by Simon Owens in U.S. News is an excellent and detailed review of the debate. The article compares open access journals to e-books: while e-books have existed for a long time, it is only in the last five years that they have really taken off, after reaching a tipping point. Owens argues that open access journals have reached that tipping point, and the academic journal publishing business (known for the huge profits they extract from university libraries) is on the verge of serious disruption.

I tend to agree with his assessment, open access journals have been flying largely under the radar for a long time, but I get the sense that they are becoming more accepted among the top researchers: when more top researchers publish in open-access journals, they will gain credibility.

The old publishing model is being destroyed by greed: journals are just too expensive, and suck too much money out of universities that should be spent funding research and paying people's salaries. Open access is the future of scientific publishing.

A small victory for open access 2

Following up from my earlier post, this article in The Economist gives a pretty good overview of the recent UK and EU move towards requiring the outputs of publicly-funded research being published as open access. The article also gives a lot of context about the different open access publishing models - the "gold" model practiced by PLoS, where authors pay a fee to publish; and the "green" model that the USA's NIH demands, whereby papers are published in traditional journals, but the journals must allow authors to publish their papers in an open repository like PubMed after one year.

So, when are we going to start seeing one of these models applied to computational intelligence journals? I'd be especially pleased if the IEEE were to adopt one of these models, as they lock every single paper they publish up behind a paywall, seemingly for all of time.

Conference paper deadline: KES-IDT 2013

The deadline for submitting papers to the 5th International Conference on Intelligent Decision Technologies (KES-IDT) is 6 January 2013. This conference will be held in Sesimbra, Portugal, 26-28 June 2013.

A small victory for open access

All taxpayer-funded research in the UK must now be published as open access papers, according to this article in the BBC. The British government will be providing £50m in subsidies for researchers to pay the fees necessary to have their work available as open access.

This is a victory for open access. But, the victory is not complete. Firstly, the £50m is coming out of general research funding, it's not new money. In other words, there will be less research done because of this, as there will be less money available to fund it. Secondly, the money is going to the established academic publishers, who are just going to use it to further pad their profits. Finally, as the article states, many journals will still not accept articles that have the relevant data available from open data repositories.

I still think that eventually, open access journals will over-whelm the old publishers. But they can only do this if the top researchers contribute quality research articles to them. Meanwhile, I personally think that the next step is for reviewers (and editors) to start demanding payment for the labour they provide to the publishers. It is we reviewers and editors who provide the quality control for the journals, it's time we got paid for it.

Would anyone be willing to sign up for a boycott of all publishers, until reviewers and editors are paid?

IEEE Transactions on Fuzzy Systems, Volume 20, Issue 3, 2012

IEEE Transactions on Fuzzy Systems, Volume 20, Issue 3, 2012

1. Grouping, Overlap, and Generalized Bientropic Functions for Fuzzy Modeling of Pairwise Comparisons
Bustince, H.; Pagola, M.; Mesiar, R.; Hullermeier, E.; Herrera, F.
Page(s): 405 - 415
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6060906

2. Analytical Structure and Characteristics of Symmetric Karnik–Mendel Type-Reduced Interval Type-2 Fuzzy PI and PD Controllers
Maowen Nie; Woei Wan Tan
Page(s): 416 - 430
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6064887

3. Delay-Dependent Decentralized H_\infty Filtering for Discrete-Time Nonlinear Interconnected Systems With Time-Varying Delay Based on the T–S Fuzzy Model
Hongbin Zhang; Hua Zhong; Chuangyin Dang
Page(s): 431 - 443
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6072261

4. Collaborative Fuzzy Clustering Algorithms: Some Refinements and Design Guidelines
Coletta, L.F.S.; Vendramin, L.; Hruschka, E.R.; Campello, R.J.G.B.; Pedrycz, W.
Page(s): 444 - 462
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6074934

5. Fuzzy Wavelet Neural Network With an Accelerated Hybrid Learning Algorithm
Davanipoor, M.; Zekri, M.; Sheikholeslam, F.
Page(s): 463 - 470
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6081924

6. Adaptive Control Schemes for Discrete-Time T–S Fuzzy Systems With Unknown Parameters and Actuator Failures
Ruiyun Qi; Gang Tao; Bin Jiang; Chang Tan
Page(s): 471 - 486
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6084736

7. Aggregation for Atanassov’s Intuitionistic and Interval Valued Fuzzy Sets: The Median Operator
Beliakov, G.; Bustince, H.; James, S.; Calvo, T.; Fernandez, J.
Page(s): 487 - 498
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6086758

8. Enhanced Interval Approach for Encoding Words Into Interval Type-2 Fuzzy Sets and Its Convergence Analysis
Dongrui Wu; Mendel, J.M.; Coupland, S.
Page(s): 499 - 513
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6086759

9. Intuitionistic Fuzzy Multiattribute Decision Making: An Interactive Method
Zeshui Xu
Page(s): 514 - 525
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6087279

10. Entailment Principle for Measure-Based Uncertainty
Yager, R.R.
Page(s): 526 - 535
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6094201

11. Learning Error Feedback Design of Direct Adaptive Fuzzy Control Systems
Yao-Chu Hsueh; Shun-Feng Su
Page(s): 536 - 545
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6097053

12. Comparing Fuzzy Partitions: A Generalization of the Rand Index and Related Measures
Hullermeier, E.; Rifqi, M.; Henzgen, S.; Senge, R.
Page(s): 546 - 556
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6104134

13. A Generalization of Distance Functions for Fuzzy c -Means Clustering With Centroids of Arithmetic Means
Junjie Wu; Hui Xiong; Chen Liu; Jian Chen
Page(s): 557 - 571
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6104135

14. Decentralized Fault-Tolerant Control for Satellite Attitude Synchronization
Junquan Li; Kumar, K.D.
Page(s): 572 - 586
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6108359

15. Fuzzy Adaptive Tracking Control of Wheeled Mobile Robots With State-Dependent Kinematic and Dynamic Disturbances
Dongkyoung Chwa
Page(s): 587 - 593
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6084735

16. Nonquadratic Stabilization of Continuous T–S Fuzzy Models: LMI Solution for a Local Approach
Jun-Tao Pan; Guerra, T.M.; Shu-Min Fei; Jaadari, A.
Page(s): 594 - 602
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6104133

Reminder: paper submission deadline for EMO 2013

A reminder that the deadline for submitting papers to the 7th International Conference on Evolutionary Multi-Criterion Optimization (EMO) 2013 is 19 August 2012. This conference will be held in Sheffield, UK, 19-22 March, 2013.

IEEE Transactions on Evolutionary Computation: Volume 16, Issue 3, 2012

Table of contents for IEEE Transactions on Evolutionary Computation Volume 16, Issue 3, 2012.

1. A Cluster and Gradient-Based Artificial Immune System Applied in Optimization Scenarios
de Mello Honorio, L.; da Silva, A.M.L.; Barbosa, D.A.
Page(s): 301 - 318
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6204227

2. Maximum Satisfiability: Anatomy of the Fitness Landscape for a Hard Combinatorial Optimization Problem
Prugel-Bennett, A.; Tayarani-Najaran, M.-H.
Page(s): 319 - 338
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6045332

3. Real-Coded Chemical Reaction Optimization
Lam, A.Y.S.; Li, V.O.K.; Yu, J.J.Q.
Page(s): 339 - 353
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6029981

4. A Study of Collapse in Bare Bones Particle Swarm Optimization
Blackwell, T.
Page(s): 354 - 372
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6029979

5. Multiobjectivization via Helper-Objectives With the Tunable Objectives Problem
Lochtefeld, D.F.; Ciarallo, F.W.
Page(s): 373 - 390
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6029982

6. Evolutionary Design of Both Topologies and Parameters of a Hybrid Dynamical System
Dupuis, J.; Zhun Fan; Goodman, E.D.
Page(s): 391 - 405
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6045329

7. Grammatical Evolution of Local Search Heuristics
Burke, E.K.; Hyde, M.R.; Kendall, G.
Page(s): 406 - 417
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6029980

8. A Multiobjective Genetic Algorithm to Find Communities in Complex Networks
Pizzuti, C.
Page(s): 418 - 430
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6045331

9. A Genetic Approach to Statistical Disclosure Control
Smith, J.E.; Clark, A.R.; Staggemeier, A.T.; Serpell, M.C.
Page(s): 431 - 441
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6036172

10. Decomposition-Based Multiobjective Evolutionary Algorithm With an Ensemble of Neighborhood Sizes
Shi-Zheng Zhao; Suganthan, P.N.; Qingfu Zhang
Page(s): 442 - 446
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6151117

Call for papers: WCCI 2014

While WCCI 2012 has only just ended, preparations for the World Congress on Computational Intelligence (WCCI) 2014 have already begun. WCCI 2014 will consist of the International Joint Conference on Neural Networks (IJCNN), the International Conference on Fuzzy Systems (FUZZ-IEEE) and the Congress on Evolutionary Computations (CEC). This congress will be held in Beijing, China, July 6-11, 2014.

The deadline for submitting papers to each of these three conferences is December 20, 2013.

Conference paper deadline: ICAISC 2013

The deadline for submitting papers to the International Conference on Artificial Intelligence and Soft Computing (ICAISC) 2013 is November 20, 2012. This conference will be held in Zakopane, Poland, June 9-13, 2013.

IEEE Transactions on Neural Networks and Learning Systems; Volume 23, Issue 7, July 2012

1. Title: L1/2 Regularization: A Thresholding Representation Theory and a Fast Solver
Authors: Zongben Xu; Xiangyu Chang; Fengmin Xu; Hai Zhang
Page(s): 1013 - 1027
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6205396

2. Title: Toward Automatic Time-Series Forecasting Using Neural Networks
Authors: Weizhong Yan
Page(s): 1028 - 1039
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6210391

3.Title: Novel Cascade FPGA Accelerator for Support Vector Machines Classification
Authors: Markos Papadonikolakis; Christos-Savvas Bouganis
Page(s): 1040 - 1052
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6197724

4. Title: Robust GRBF Static Neurocontroller With Switch Logic for Control of Robot Manipulators
Authors: Juan Ignacio Mulero-Martínez
Page(s): 1053 - 1064
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6198898

5. Title: VLSI Implementation of a Bio-Inspired Olfactory Spiking Neural Network
Authors: Hung-Yi Hsieh; Kea-Tiong Tang
Page(s): 1065 - 1073
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6202348

6. Title: Transductive Ordinal Regression
Authors: Chun-Wei Seah; Ivor W. Tsang; Yew-Soon Ong
Page(s): 1074 - 1086
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6203451

7. Title: Online Nonnegative Matrix Factorization With Robust Stochastic Approximation
Authors: Naiyang Guan; Dacheng Tao; Zhigang Luo; Bo Yuan
Page(s): 1087 - 1099
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6203594

8. Title: SSC: A Classifier Combination Method Based on Signal Strength
Authors: Haibo He; Yuan Cao
Page(s): 1100 - 1117
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6204134

9. Title: Online Optimal Control of Affine Nonlinear Discrete-Time Systems With Unknown Internal Dynamics by Using Time-Based Policy Update
Authors: Travis Dierks; Sarangapani Jagannathan
Page(s): 1118 - 1129
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6208889

10. Title: Reproducing Kernel Hilbert Space Approach for the Online Update of Radial Bases in Neuro-Adaptive Control
Authors: Hassan A. Kingravi; Girish Chowdhary; Patricio A. Vela; Eric N. Johnson
Page(s): 1130 - 1141
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6208915

11. Title: Simple Proof of Convergence of the SMO Algorithm for Different SVM Variants
Authors: Jorge López; José R. Dorronsoro
Page(s): 1142 - 1147
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6193217

12. Title: RBF Networks Under the Concurrent Fault Situation
Authors: Chi-Sing Leung; John Pui-Fai Sum
Page(s): 1148 - 1155
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6203419

13. Title: Neural Network-Based Distributed Attitude Coordination Control for Spacecraft Formation Flying With Input Saturation
Authors: An-Min Zou; Krishna Dev Kumar
Page(s): 1155 - 1162
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6203597

14. Title: Universal Neural Network Control of MIMO Uncertain Nonlinear Systems
Authors: Qinmin Yang; Zaiyue Yang; Youxian Sun
Page(s): 1163 - 1169
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6203596

15. Title: Spectral Graph Optimization for Instance Reduction
Authors: Konstantinos Nikolaidis; Eduardo Rodriguez-Martinez; John Yannis Goulermas; Q. H. Wu
Page(s): 1169 - 1175
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6208890

Reminder: paper submission deadline for IEEE-SSCI 2013

A reminder that 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.

Reminder: paper submission deadline for Fuzz-IEEE 2013

A reminder that the deadline for submitting papers to the IEEE Conference on Fuzzy Systems (Fuzz-IEEE) 2013 is 5 January, 2013. This conference will be held in Hyderabad, India, 7-10 July, 2013.

Reminder: IEEE CIS Facebook Photo Competition

The IEEE Computational Intelligence Society are running a photo competition on Facebook. See the flyer below to find out how to enter.

Google Brain

The so-called Google Brain has been in the news the last couple of days (see for example here, here and here, and see here for coverage from the ABC, including part of an interview I did with them on the subject).

The news coverage has focussed on how the machine learned to recognise cats, because cats are cute. Reading the original paper gives a more nuanced view of the technology. The researchers constructed a colossal neural network with one billion neurons, implemented over 1000 16-processor servers. They then presented it with ten million images taken from YouTube, and left it to train for three days before looking to see what it had learned.

The researchers knew that the three most common images on YouTube were cats, human faces, and human bodies. So, they presented images drawn from independent data sets (that is, data sets that were not involved in training the network) that were known to be of cats, faces or bodies, and saw which parts of the network activated. By examining the activations within the network, they found that there were prototypes of cats, faces and bodies within the network. That is, they showed that the network had formed its own exemplars of these objects.

There are four main technical innovations in this paper:

1) The size of the network, which had one billion artificial neurons.

2) The technique they used to reduce the interconnections between the elements of the network, to make it easier to execute in parallel across the 16 000 processors they used.

3) The number of images (ten million) used to train the network.

4) The size of the images used (200 x 200 pixels, which is larger than most).

The network did not learn to recognise cats, faces, or bodies. It still doesn't know what a cat is, or what a face is, or what a human body is. It has no concept of what the images represent. But even so, it still has potential: neural networks have finally reached the age of Big Data.

Call for papers: ICANNGA 2013

The paper submission deadline for the International Conference on Adaptive and Natural Computing Algorithms (ICANNGA) 2013 is 8 October, 2013. This conference will be held in Lausanne, Switzerland, April 4-6, 2013.

Call for papers: AROB 2013

The deadline for submitting papers to the 18th International Symposium on Artificial Life and Robotics (AROB) 2013 is 1 September, 2012. This symposium will be held in Daejeon, Korea, January 30 - February 1st, 2013.

Reminder: paper submission deadline for iFuzzy 2012

A reminder that the deadline for papers submitted to the International Conference on Fuzzy Theory and its Application 2012 is 20 August 2012. This conference will be held in Taiching, Tuiwan, 16-18 November, 2012.

Reminder: conference paper deadline for ICIIC 2012

A reminder that the paper submission deadline for the International Conference on Information and Intelligent Computing 2012 is 20 July 2012. This conference will be held in Chengdu, China, 8-9 December, 2012.

Paper submission deadline: EMO 2013

The deadline for submitting papers to the 7th International Conference on Evolutionary Multi-Criterion Optimization (EMO) 2013 is 19 August 2012. This conference will be held in Sheffield, UK, 19-22 March, 2013.

Call for papers: FOGA 2013

The deadline for submitting papers to the Foundations of Genetic Algorithms (FOGA) 2013 is 1 August 2012. This conference will be held in Adelaide, Australia, 16-20 January, 2013.

I am currently living in Adelaide, and can highly recommend a visit to this beautiful city. My only warning is that in January, the temperature often exceeds 40 degrees!

More developments in academic journals

There has been a new development in open-access academic journals (see my previous posts on this matter here, here, here, here and here). Two articles, here and here, describe PeerJ, a new approach to open-access journals. Whereas the traditional publishers charge readers for access to content, and open-access journals charge authors per-paper publication charges, PeerJ charges authors a one-off lifetime publishing fee. As long as all of the authors (or at least the first 12 authors) of a paper are subscribers, the authors can submit as many papers as they like for no further cost. The papers are peer-reviewed, and will be available for free. There are different subscriptions available, ranging from a lower-cost option that allows for a fixed number of papers per year, up to a more expensive "all you can eat" model with no restrictions.

PeerJ is starting with life sciences first: given the large number of researchers and papers coming out of the life sciences, this seems quite sensible and is more likely to give them a solid revenue stream early-on. It is interesting that they are requiring each member to review at least one paper per year, which neatly gets around the problems associated with finding enough reviewers for papers.

I suspect that the computational intelligence community does not have enough researchers to make such a model viable at the rates PeerJ are advertising. So, such a journal would probably have to charge higher subscription rates, or charge an annual or bi-annual fee.

But these are all ways for publishers to make money off of free content (submitted papers) and free labour, in the form of reviewers (who are actually paying for the privilege in the case of PeerJ). I'm not the first person to suggest this, but why not spend some of that money on reviewers? That is, when a reviewer completes an on-time review, pay them a small gratuity (like 100-200 Euros). That would motivate reviewers to do their reviews on time (if you're working for free, there is less motivation to do the work quickly). It would also be a more fair system, as those who provide the most valuable service in the publishing process would be compensated for their time and efforts. Finally, it might make it easier to find reviewers for papers: my own editorial experience has shown me how hard it can be to find reviewers for a paper. I review about a dozen papers per year, so this scheme wouldn't provide me with a living, but it would cover many of the incidental expenses that come up over the year.

Instead of a Boycott Elsevier pledge website, do we need a website where people can pledge to no longer review any papers until publishers start paying? Would anyone sign up for that?

Publishing and perishing under gameable metrics 2

This article about the Australian Excellence in Research for Australia (ERA) initiative discusses how the process by which Australian universities and academic are assessed is flawed. It also discusses how Australian institutions have been gaming the metrics, like certain New Zealand institutions have been accused of doing.

In this previous post I described how any metric by which an institution or academic is assessed can be gamed. That is, any way in which an academic or institution is assessed can be manipulated by that institution to gain a higher score. In this post, I discussed how this has a negative effect on the teaching performance of an institution. By removing staff who do not perform well in research assessments due to a heavy teaching load, the institution can lift their research scores, but at the cost of lowering their teaching performance. As the article mentions, teaching is not assessed, so the process optimises towards a single metric at the expense of all others. This is not helpful for the long-term viability of an institution, as undergraduates will not want to attend an institution with a poor reputation for teaching.

This situation is almost certain to increase the use of contract lecturers, as contract lecturers are, as I understand it, exempt from assessment. I've already described why increasing contract lecturers is a bad idea, mostly because of a lack of job security and satisfaction for the contract lecturers, as well as a lack of continuity in teaching from the point of view of the students.

It is becoming increasingly apparent to me that assessing institutions is not as useful as assessing individuals, and that, in today's highly-mobile world, the reputation of an institution is no longer as important as the reputation of an individual researcher. This raises an interesting question:

What would happen if research performance based funding were given directly to the researchers based on their own individual performance, rather than their institutions being given extra funding based on the collective research performance of their staff?

The article linked at the start of this post does an excellent job of describing the problems with collective assessments (like what does it mean if you have one researcher ranked 1 and one ranked 5 - do they have a collective performance of 3? What does that even mean?).

Individual funding would remove a lot of the financial motivation for institutions to game the system, although it wouldn't eliminate it (institutions would still make money by charging the individual researchers over-heads, but these could be capped). Under the current Australian and New Zealand systems, individuals are assessed anyway, so it doesn't require any great changes to the current assessment process. One downside (and it could be a stonking big downside) is that early-career researchers would probably do poorly under this model. Early-career are already disadvantaged by management practices designed to game the system, and a simple weighting mechanism accounting for the length of time an individual has been doing research would go a long way to help. This would encourage researchers to start publishing early (which is essential to master the art of scientific publishing) and to publish consistently (which is essential to maintain your publishing skills). Another downside would be senior researchers taking credit for the work of junior researchers. But, again, this happens anyway, even though it is profoundly unethical. Under this system, though, it would no longer be just unethical, it would be criminal fraud.

Such a scheme could only be successful if it were paired with a scheme for assessing and rewarding teaching. While I have stated several times that an academic in a permanent position who is not publishing is not doing their job, an academic with a low (but not non-existent) research output and a strong teaching performance is an asset to an institution. Therefore, it is, in my opinion, imperative that an objective metric for teaching performance be implemented as soon as possible. That way, quality teachers, as well as quality researchers, would be recognised and rewarded. Those who do both (and this is the ideal for an academic, to teach and do research) would score even higher.

International Neural Network Society Social Media sites

The International Neural Network Society (INNS) has established a presence on several popular social media sites. The goals of this initiative are:

- To promote the membership and activities of the INNS
- To better bring the members of the INNS relevant information about the activities of the society
- To help facilitate networking between members

Members of the INNS and other interested people are invited join us on the following INNS social media sites:

Blog: http://innsorg.blogspot.com/

Twitter: http://www.twitter.com/#!/INNSorg

Facebook: http://www.facebook.com/pages/International-Neural-Network-Society/110873922384495

LinkedIn: http://www.linkedin.com/groups?gid=2985057

Google+: https://plus.google.com/106354210782755399208/posts

IEEE Transactions on Autonomous Mental Development, Vol.4, No.1, March 2012

1. Episodic-Like Memory for Cognitive Robots
Stachowicz, D.; Kruijff, G.M.
Page(s): 1-16
Digital Object Identifier: 10.1109/TAMD.2011.2159004
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5871687

2. A Model to Explain the Emergence of Imitation Development Based on Predictability Preference
Minato, T.; Thomas, D.; Yoshikawa, Y.; Ishiguro, H.
Page(s): 17-28
Digital Object Identifier: 10.1109/TAMD.2011.2158098
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5782935

3. Symbolic Models and Emergent Models: A Review
Juyang Weng
Page(s): 29-53
Digital Object Identifier: 10.1109/TAMD.2011.2159113
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5872008

4. A Behavior-Grounded Approach to Forming Object Categories: Separating Containers From Noncontainers
Griffith, S.; Sinapov, J.; Sukhoy, V.; Stoytchev, A.
Page(s): 54-69
Digital Object Identifier: 10.1109/TAMD.2011.2157504
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5778950

5. Autonomous Learning of High-Level States and Actions in Continuous Environments
Mugan, J.; Kuipers, B.
Page(s): 70-86
Digital Object Identifier: 10.1109/TAMD.2011.2160943
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5936108

6. A Goal-Directed Visual Perception System Using Object-Based Top-Down Attention
Yuanlong Yu; Mann, G.K.I.; Gosine, R.G.
Page(s): 87-103
Digital Object Identifier: 10.1109/TAMD.2011.2163513
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5978202