Monday, March 31, 2014

IEEE Transactions on Evolutionary Computation Volume 18, Number 2, April 2014

PAPERS

1. Artificial Biochemical Networks: Evolving Dynamical Systems to Control Dynamical Systems
Author(s): M. A. Lones, L. A. Fuente, A. P. Turner, L. S. D. Caves, S. Stepney, S. L. Smith, and A. M. Tyrrell
Pages: 145-166

2. Multi-Objective Optimization by Using Evolutionary Algorithms: The p-Optimality Criteria
Author(s): E. Carre ̃no Jara
Pages: 167-179

3. A Gaussian Process Surrogate Model Assisted Evolutionary Algorithm for Medium Scale Expensive Optimization Problems
Author(s): B. Liu, Q. Zhang, and G. G. E. Gielen
Pages: 180-192

4. Automatic Design of Scheduling Policies for Dynamic Multi-objective Job Shop Scheduling via Cooperative Coevolution Genetic Programming
Author(s): S. Nguyen, M. Zhang, M. Johnston, and K. Chen Tan
Pages: 193-208

5. An Improved Differential Evolution Algorithm for Practical Dynamic Scheduling in Steelmaking-Continuous Casting Production
Author(s): L. Tang, Y. Zhao, and J. Liu
Pages: 209-225

6. Frequency Fitness Assignment
Author(s): T. Weise, M. Wan, P. Wang, K. Tang, A. Devert, and X. Yao
Pages: 226-243

7. Localization of License Plate Number Using Dynamic Image Processing Techniques and Genetic Algorithms
Author(s): G. Abo Samra and F. Khalefah
Pages: 244-257

8. Comparison Study of Swarm Intelligence Techniques for the Annual Crop Planning Problem
Author(s): S. Chetty and A. O. Adewumi
Pages: 258-268

9. Fuzzy-Based Pareto Optimality for Many-Objective Evolutionary Algorithms
Author(s): Z. He, G. G. Yen, and J. Zhang
Pages: 269-287

10. A Distance-Based Ranking Model Estimation of Distribution Algorithm for the Flowshop Scheduling Problem
Author(s): J. Ceberio, E. Irurozki, A. Mendiburu, and J. A. Lozano
Pages: 286-300

LETTER

11. A Discrete Firefly Algorithm for the Multi-Objective Hybrid Flowshop Scheduling Problems
Author(s): M. K. Marichelvam, T. Prabaharan, and X. S. Yang
Pages: 301

Friday, March 28, 2014

IEEE Transactions on Fuzzy Systems Volume 22, Number 2, April 2014

REGULAR PAPERS

1. Fuzzy Approximation-Based Adaptive Control of Nonlinear Delayed Systems With Unknown Dead Zone
Author(s): B.Chen,X.Liu,K.Liu,and C.Lin
Pages: 237-248

2. Output Feedback Predictive Control With One Free Control Move for Nonlinear Systems Represented by a Takagi–Sugeno Model
Author(s): B.Ding and X.Ping
Pages: 249-263

3. Individual Decision Making Can Drive Epidemics: A Fuzzy Cognitive Map Study
Author(s): S. Mei, Y. Zhu, X. Qiu, X. Zhou, Z. Zu, A. V. Boukhanovsky, and P. M. A. Sloot
Pages: 264-273

4. Adaptive Fault Diagnosis for T–S Fuzzy Systems With Sensor Faults and System Performance Analysis
Author(s): Q.Shen, B.Jiang, and P.Shi
Pages: 274-285

5. Adaptive Fuzzy Hierarchical Sliding-Mode Control for the Trajectory Tracking of Uncertain Underactuated Nonlinear Dynamic Systems
Author(s): C.-L.Hwang, C.-C.Chiang, and Y.-W.Yeh
Pages: 286-299

6. Atanassov’s Intuitionistic Fuzzy Programming Method for Heterogeneous Multiattribute Group Decision Making With Atanassov’s Intuitionistic Fuzzy Truth Degrees
Author(s): S.-P. Wan and D.-F. Li
Pages: 300-312

7. Novel Stability Criteria for T–S Fuzzy Systems
Author(s): X. Zhao, L. Zhang, P. Shi, and H. R. Karimi
Pages: 313-323

8. A Fuzzy Model With Online Incremental SVM and Margin-Selective Gradient Descent Learning for Classification Problems
Author(s): W.-Y. Cheng and C.-F. Juang
Pages: 324-337

9. Adaptive Fuzzy Observer-Based Active Fault-Tolerant Dynamic Surface Control for a Class of Nonlinear Systems With Actuator Faults
Author(s): Q.Shen, B.Jiang, and V.Cocquempot
Pages: 338-349

10. Universal Fuzzy Integral Sliding-Mode Controllers Based on T–S Fuzzy Models
Author(s): Q. Gao, L. Liu, G. Feng, Y. Wang, and J. Qiu
Pages: 350-362

11. What and When Can We Gain From the Kernel Versions of C-Means Algorithm?
Author(s): N. R. Pal and K. Sarkar
Pages: 363-379

12. Dissipativity Analysis and Synthesis for Discrete-Time T–S Fuzzy Stochastic Systems With Time-Varying Delay
Author(s): L.Wu, X.Yang, and H.-K.Lam
Pages: 380-394

13. Making Use of Partial Knowledge About Hidden States in HMMs: An Approach Based on Belief Functions
Author(s): E.Ramasso and T.Denoeux
Pages: 395-405

14. Decentralized Fuzzy Observer-Based Output-Feedback Control for Nonlinear Large-Scale Systems: An LMI Approach
Author(s): G.B.Koo, J.B.Park, and Y.H.Joo
Pages: 406-419

15. L_p Consonant Approximations of Belief Functions
Author(s): F. Cuzzolin
Pages: 420-436

16.
Adaptive Fuzzy Control for Multilateral Cooperative Teleoperation of Multiple Robotic Manipulators Under Random Network-Induced Delays
Author(s): Z. Li, Y. Xia, and F. Sun
Pages: 437-450

SHORT PAPERS

17. TSK Observers for Discrete Type-1 and Type-2 FuzzySystems
Author(s): M. S. Fadali and S. Jafarzadeh
Pages: 451-458

18. Robust H∞ Control of TS Fuzzy Time-Delay Systems via a New Sliding-Mode Control Scheme
Author(s): Q.Gao, G.Feng, Z.Xi, Y.Wang, and J.Qiu
Pages: 459-464

19. Toward Necessity of Parametric Conditions for Monotonic Fuzzy Systems
Author(s): J.-M. Won and F. Karray
Pages: 465-470

Thursday, March 27, 2014

Conference paper deadline: CEC 2015

The deadline for submitting papers to the IEEE Congress on Evolutionary Computation (IEEE CEC) 2015 is December 19, 2014. This conference will be held in Sendai, Japan, 25-28 May, 2015.

Wednesday, March 26, 2014

Conference paper deadline: PRICAI 2014

The deadline for submitting papers to the 13th Pacific Rim International Conference on Artificial Intelligence (PRICAI) 2014 is June 29, 2014. This conference will be held in the Gold Coast, Australia, 1-5 December, 2014.

Monday, March 24, 2014

Conference paper deadline: ICONIP 2014

The deadline for submitting papers to the 21st International Conference on Neural Information Processing (ICONIP) 2014 is May 2, 2014. This conference will be held in Kuching, Malaysia, 3-6 November, 2014.

Thursday, March 20, 2014

Finding an academic job

Finding a job for any profession is difficult, but finding a job in academia can be ridiculously hard. Since I finished my PhD ten years ago, I've had two periods of unemployment, totalling more than six months out of work. Since I was the sole income-earner for my family at the time, those periods were particularly difficult and stressful to get through, but I got through them, as much by luck as by design.

I've come across a collection of articles on finding academic jobs, that I wanted to share and comment on. I tend to agree with what most of them have to say, even though they're not specific to computational intelligence in particular or even computer science or engineering in general.

The first discusses whether you should even go for an academic job. For computer scientists it is probably easier to go into industry with a PhD than it is for other PhD graduates. The tech industry is always strong somewhere, and it is always growing, so there are always jobs to be had. In my own country of New Zealand, at any one time there are usually between two and three thousand vacancies in the IT sector, and that's out of a country of around four million.

The second article discusses ways to improve your chances of getting an academic job. The authors mention engaging with the community, publishing papers and emphasising transferable skills. I've actually had one supervisor tell me that there is nothing more important than publishing papers, while this article argues that too much publishing runs the risk of establishing nothing more than an unfocussed research record, and this article argues that teaching experience, including experience designing and administering courses, is very important for getting an academic job. Even though I was more interested in the research side of things during my Honours year, I still worked as a tutor for a database course, and during my post-grad years I tutored computational intelligence courses. Near the end of my studies, I worked full-time as a teaching fellow (I believe in the USA that would be Teaching Assistant, but I can't be sure) and did re-work and administer courses. I am quite certain that this experience helped me to get the job I have now.

Having decided to stay in academia, and done the ground-work to enter the academic profession, the next step is to find an academic job. When you've identified a job you are interested in, the first thing you must do it get your academic CV in order. There are several common mistakes you must avoid in this document, since one mistake is all it takes for a recruiter (who are not academics) to discard your entire application. The previous two articles have some very good pieces of advice for laying out your CV, and I have applied several of them to improve my own CV.

Things like career objective statements should also be left out of a CV. My current job means that I regularly receive unsolicited emails complete with CV from people wanting a teaching job in my department, and most of them have things like career objective statements that have nothing whatsoever to do with my department or any kind of teaching job. Nothing says "desperate blanket bombing" like failing to do even a minimum of research about the place you are sending your job application to.

The other major component of an application for an academic job is the cover letter. This should also be specific for the position you are applying for, it should cover all of the criteria mentioned in the job advertisement, and it should be short. If you make it too long and detailed, then you run the risk of boring the recruiter before they finish reading, which usually results in your application being thrown away.

If you have a compelling CV, and have written a very good cover letter that shows that you are very well suited to the job, then you might get an interview. This article talks about how to prepare for an interview. One of the points in it that I would emphasise is the need to do your research before the interview. One of the fundamental rules in the Art of War is "Know yourself, and know others, and you shall have one hundred victories in one hundred battles". This applies to interviews as well! Know who is going to be interviewing you: have they published with anyone you know? Is there any other connection? What relationship does their research have to yours? This article also has some tips on how to handle tricky interview questions. Some questions just can't be answered well, like the question I got once about how I demonstrated an awareness of diversity in the classroom (I'm from the whitest district in New Zealand and I married a Chinese, I think that shows a pretty good awareness of diversity). Obviously, some self-confidence is very important, and I've been lucky in that a couple of times some really good people have boosted my self-esteem just before interviews.

Usually, by the end of an interview, I know whether I've gotten the job or not, just by the way the interview went. If I have struggled with any of the questions, then I probably won't get it. If it's gone smoothly, then I know I've got a much better chance. There have been a couple of cases where the interview went well and I still didn't get the job, but those were years ago and for positions that were probably above my skill level at the time.

Job hunting is brutal, and academic positions invariably attract a lot of applications (especially New Zealand positions, as for some reason a lot of people want to move here). The last time I was out of work, I sent off two dozen applications, which resulted in three interviews, which led to two job offers. And that was with a PhD, four years teaching experience, almost five years post-doc experience, and more than forty publications. But, if you stick to it, you will find a job. It might not be the job you first had in mind when you started, but it will be just as good, and any job is good experience if you're clever about how you do it.

Wednesday, March 19, 2014

IEEE Transactions on Neural Networks and Learning Systems Volume 25, Number 4, April 2014

REGULAR PAPERS

1. Dynamic Uncertain Causality Graph for Knowledge Representation and Probabilistic Reasoning: Statistics Base, Matrix, and Application
Author(s): Q. Zhang, C. Dong, Y. Cui, and Z. Yang
Pages: 645-663

2. T2FELA: Type-2 Fuzzy Extreme Learning Algorithm for Fast Training of Interval Type-2 TSK Fuzzy Logic System
Author(s): Z. Deng, K.-S. Choi, L. Cao, and S. Wang
Pages: 664-676

3. Adaptive Quasi-Newton Algorithm for Source Extraction via CCA Approach
Author(s): W.-T. Zhang, S.-T. Lou, and D.-Z. Feng
Pages: 677-689

4. Lagrange Stability of Memristive Neural Networks With Discrete and Distributed Delays
Author(s): A. Wu and Z. Zeng
Pages: 690-703

5. Attractivity Analysis of Memristor-Based Cellular Neural Networks With Time-Varying Delays
Author(s): Z. Guo, J. Wang, and Z. Yan
Pages: 704-717

6. Novel Neural Control for a Class of Uncertain Pure-Feedback Systems
Author(s): Q. Shen, P. Shi, T. Zhang, and C.-C. Lim
Pages: 718-727

7. An Ordered-Patch-Based Image Classification Approach on the Image Grassmannian Manifold
Author(s): C. Xu, T. Wang, J. Gao, S. Cao, W. Tao, and F. Liu
Pages: 728-737

8. Artificial Neural Networks for Control of a Grid-Connected Rectifier/Inverter Under Disturbance, Dynamic and Power Converter Switching Conditions
Author(s): S. Li, M. Fairbank, C. Johnson, D. C. Wunsch, E. Alonso, and J. L. Proaño
Pages: 738-750

9. A Stochastic Mean Field Model for an Excitatory and Inhibitory Synaptic Drive Cortical Neuronal Network
Author(s): Q. Hui, W. M. Haddad, J. M. Bailey, and T. Hayakawa
Pages: 751-763

10. RandomBoost: Simplified Multiclass Boosting Through Randomization
Author(s): S. Paisitkriangkrai, C. Shen, Q. Shi, and A. van den Hengel
Pages: 764-779

11. A Unified Learning Framework for Single Image Super-Resolution
Author(s): J. Yu, X. Gao, D. Tao, X. Li, and K. Zhang
Pages: 780-792

12. L1-Norm Kernel Discriminant Analysis via Bayes Error Bound Optimization for Robust Feature Extraction
Author(s): W. Zheng, Z. Lin, and H. Wang
Pages: 793-805

BRIEF PAPERS

13. Online Motor Fault Detection and Diagnosis Using a Hybrid FMM-CART Model
Author(s): M. Seera and C. P. Lim
Pages: 806-811

14. Feature-Based Ordering Algorithm for Data Presentation of Fuzzy ARTMAP Ensembles
Author(s): T. H. Oong and N. A. M. Isa
Pages: 812-818

16. Self-Organization in Autonomous, Recurrent, Firing-Rate CrossNets With Quasi-Hebbian Plasticity
Author(s): T. J. Walls and K. K. Likharev
Pages: 819-823

17. A Recurrent Neural Network for Solving Bilevel Linear Programming Problem
Author(s): X. He, C. Li, T. Huang, C. Li, and J. Huang
Pages: 824-829

18. Local Stability Analysis of Discrete-Time, Continuous-State, Complex-Valued Recurrent Neural Networks With Inner State Feedback
Author(s): M. Mostafa, W. G. Teich, and J. Lindner
Pages: 830-842

19. Sparse Bayesian Extreme Learning Machine for Multi-classification
Author(s): J. Luo, C.-M. Vong, and P.-K. Wong
Pages: 843

Tuesday, March 18, 2014

IEEE Transactions on Autonomous Mental Development, Volume 6, Number 1, March 2014

1. An Approach to Subjective Computing: A Robot That Learns From Interaction With Humans
Author(s): P. Grüneberg and K. Suzuki
Pages: 5-18

2. LIDA: A Systems-level Architecture for Cognition, Emotion, and Learning
Author(s): S. Franklin, T. Madl, S. D’Mello, and J. Snaider
Pages: 19-41

3. Development of First Social Referencing Skills: Emotional Interaction as a Way to Regulate Robot Behavior
Author(s): S. Boucenna, P. Gaussier, and L. Hafemeister
Pages: 42-55

4. Object Learning Through Active Exploration
Author(s): S. Ivaldi, S. M. Nguyen, N. Lyubova, A. Droniou, V. Padois, D. Filliat, P.-Y. Oudeyer, and O. Sigaud
Pages: 56-72

5. Erratum to "Modeling Cross-Modal Interactions in EarlyWord Learning"
Pages: 73

Monday, March 17, 2014

IEEE Transactions on Computational Intelligence and AI in Games - Volume 6, Number 1, March 2014

1. General Self-Motivation and Strategy Identification: Case Studies Based on Sokoban and Pac-Man
Author(s): T. Anthony, D. Polani, and C. L. Nehaniv
Pages: 1-17

2. Passing a Hide-and-Seek Third-Person Turing Test
Author(s): A. Cenkner, V. Bulitko, M. Spetch, E. Legge, C. G. Anderson, and M. Brown
Pages: 18-30

3. Solving the Physical Traveling Salesman Problem: Tree Search and Macro Actions
Author(s): D. Perez, E. J. Powley, D. Whitehouse, P. Rohlfshagen, S. Samothrakis, P. I. Cowling, and S. M. Lucas
Pages: 31-45

4. Two Online Learning Playout Policies in Monte Carlo Go: An Application of Win/Loss States
Author(s): J. Basaldúa, S. Stewart, J. M. Moreno-Vega, and P. D. Drake
Pages: 46-54

5. DeepQA Jeopardy! Gamification: A Machine-Learning Perspective
Author(s): A. K. Baughman, W. Chuang, K. R. Dixon, Z. Benz, and J. Basilico
Pages: 55-66

6. A Micromanagement Task Allocation System for Real-Time Strategy Games
Author(s): K. D. Rogers and A. A. Skabar
Pages: 67-77

7. Procedural Generation of Dungeons
Author(s): R. van der Linden, R. Lopes, and R. Bidarra
Pages: 78-89

Friday, March 14, 2014

Reminder: paper submission deadline for IEEE SSCI 2014

A reminder that the deadline for submitting papers to the IEEE Symposium Series on Computational Intelligence (SSCI) 2014 is 15 June 2014. This group of symposia will be held in Orlando, Florida, 9-12 December, 2014.

Friday, March 7, 2014

IEEE SMC 2014 Special Session: Autonomous Learning and Evolving Intelligence

Below is a call for papers for a special session in the 2014 IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC). This conference will be held in San Diego, California, October 5-8, 2014.


Autonomous Learning and Evolving Intelligence

Synopsis

The special session is focussed on addressing autonomous learning in computational systems in a setting where the role of the human is to merely to start/stop the process and monitor it online. It is a specific branch of machine learning, where the computer system is expected to learn for itself within a dynamically evolving and challenging environment complex processes without heuristic input or prior training.

To achieve autonomous learning, a computer develops a form of intelligence that can evolve and adapt to its surroundings. A system that learns and evolves automatically should also operate in real-time. Currently DARPA have a challenge running for robots to operate autonomously in inhospitable environments; NSF is also recognising autonomous learning as a significant topic of research; large companies such as IBM, BT etc. also have programmes in autonomic computing and related disciplines. The objective of the proposed special session is to bring together people from academia and industry to introduce papers that look at addressing some of the fundamental problems or stumbling blocks found when a computer must learn for itself and evolve to it's surroundings.

Indicative Topics /Areas (not limited to)

  • Autonomous Learning
  • Autonomous Video Analytics
  • Intelligence and Adaptive Systems
  • Adaptive and Self-calibrating Sensor Systems
  • Autonomous Fuzzy rule-based Systems
  • Anomaly Detection
  • Fault Detection and Identification
  • Evolving Clustering
  • Evolving Classification Methods
  • Adaptive Behaviour Models
  • Robotic Systems

Submission details

Papers should not exceed 8 pages in length, papers over 6 pages in length are charged extra per page (up to a max of 2). Manuscript for a Special Session should NOT be submitted in duplication to any other regular or special session and should be submitted to SMC 2014 main conference online submission system on SMC 2014 conference website. All submitted papers of Special Session have to undergo the same review process (a t least two reviewers). The technical reviewers for each Special Session paper will be members of the SMC 2014 Program Committee and qualified peer-reviewers to be nominated by the Special Session organizers.

Special Session organizer

Plamen Angelov
University of Lancaster, UK

Important Dates

April 7, 2014
Submission of a full-length paper

May 25, 2014
Acceptance/Rejection notification

July 9, 2014
Final camera-ready paper submission

Thursday, March 6, 2014

Conference paper deadline: WCCS 14

The deadline for submitting abstracts to the World Congress on Complex Systems (WCCS) 2014 is 15 May, 2014. This conference will be held in Agadir, Morocco, November 10-14, 2014.

Tuesday, March 4, 2014

Evolving Systems Volume 5, Number 1, 2014

1. Editorial: Applications, results and future direction (EAIS 12)
Author(s): José Antonio Iglesias & Igor Škrjanc

2. A robust fuzzy adaptive law for evolving control systems
Author(s):Sašo Blažič , Igor Škrjanc & Drago Matko

3. Fault-tolerant gait learning and morphology optimization of a polymorphic walking robot
Author(s):David Johan Christensen , Jørgen Christian Larsen & Kasper Stoy

4. Elastic Adaptive Dynamics Methodology on Ontology Matching on Evolving Folksonomy Driven Environment
Author(s):Massimiliano Dal Mas

5. Dynamic learning in cognitive robotics through a procedural long term memory
Author(s):Francisco Bellas , Pilar Caamaño , Andrés Faiña & Richard J. Duro

6. Adaptive evolving strategy for dextrous robotic manipulation
Author(s):César Arismendi , David Álvarez , Santiago Garrido & Luis Moreno

Monday, March 3, 2014

Neural Networks, Volume 52, Pages 1-76, April 2014

1. Pairwise constrained concept factorization for data representation
Pages: 1-17
Author(s): Yangcheng He, Hongtao Lu, Lei Huang, Saining Xie
   
2. Hybrid extreme rotation forest
Pages: 33-42
Author(s): Borja Ayerdi, Manuel Graña
   
3. Policy oscillation is overshooting
Pages: 43-61
Author(s): Paul Wagner

4. NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data
Pages: 62-76
Author(s): Nikola K. Kasabov

5. Construction of a Boolean model of gene and protein regulatory network with memory
Pages: 18-24
Author(s): Meng Yang, Rui Li, Tianguang Chu

6. Nonsmooth finite-time stabilization of neural networks with discontinuous activations
Pages: 25-32
Author(s): Xiaoyang Liu, Ju H. Park, Nan Jiang, Jinde Cao

Friday, February 21, 2014

IEEE Transactions on Neural Networks and Learning Systems: Volume 25, Issue 3, March 2014

1. A Survey on CPG-Inspired Control Models and System Implementation
Author(s): Junzhi Yu; Min Tan; Jian Chen; Jianwei Zhang
Pages: 441 - 456

2. Robust Model Predictive Control of Nonlinear Systems With Unmodeled Dynamics and Bounded Uncertainties Based on Neural Networks
Author(s): Zheng Yan; Jun Wang
Pages: 457 - 469

3. Multi-Level Fuzzy Min-Max Neural Network Classifier
Author(s): Reza Davtalab; Mir Hossein Dezfoulian; Muharram Mansoorizadeh
Pages: 470 - 482

4. Adaptive Identifier for Uncertain Complex Nonlinear Systems Based on Continuous Neural Networks
Author(s): Mariel Alfaro-Ponce; Amadeo Arguelles Cruz; Isaac Chairez
Pages: 483 - 494

5. Function Approximation Using Combined Unsupervised and Supervised Learning
Author(s): Peter Andras
Pages: 495 - 505

6. Active Learning of Pareto Fronts
Author(s): Paolo Campigotto; Andrea Passerini; Roberto Battiti
Pages: 506 - 519

7. Learning Harmonium Models With Infinite Latent Features
Author(s): Ning Chen; Jun Zhu; Fuchun Sun; Bo Zhang
Pages: 520 - 532

8. A Class of Quaternion Kalman Filters
Author(s): Cyrus Jahanchahi; Danilo P. Mandic
Pages: 533 - 544

9. Neural Network for Nonsmooth, Nonconvex Constrained Minimization Via Smooth Approximation
Author(s): Wei Bian; Xiaojun Chen
Pages: 545 - 556

10. Nonbinary Associative Memory With Exponential Pattern Retrieval Capacity and Iterative Learning
Author(s): Amir Hesam Salavati; K. Raj Kumar; Amin Shokrollahi
Pages: 557 - 570

11. A Constrained Backpropagation Approach for the Adaptive Solution of Partial Differential Equations
Author(s): Keith Rudd; Gianluca Di Muro; Silvia Ferrari
Pages: 571 - 584

12. A Robust and Scalable Neuromorphic Communication System by Combining Synaptic Time Multiplexing and MIMO-OFDM
Author(s): Narayan Srinivasa; Deying Zhang; Beayna Grigorian
Pages: 585 - 608

13. ERNN: A Biologically Inspired Feedforward Neural Network to Discriminate Emotion From EEG Signal
Author(s): Reza Khosrowabadi; Chai Quek; Kai Keng Ang; Abdul Wahab
Pages: 609 - 620

14. Policy Iteration Adaptive Dynamic Programming Algorithm for Discrete-Time Nonlinear Systems
Author(s): Derong Liu; Qinglai Wei
Pages: 621 - 634

15. Reinforcement Learning Output Feedback NN Control Using Deterministic Learning Technique
Author(s): Bin Xu; Chenguang Yang; Zhongke Shi
Pages: 635 - 641

Thursday, February 20, 2014

Conference papers

I've just finished reviewing a pile of papers for some upcoming conference: IJCNN 2014, and EAIS 2014. While these papers represent some good work, in some cases their presentation leaves a lot to be desired. After spending my post-doc career in ecology, I have come to the conclusion that authors in our community could learn something from the way papers are written in other sciences.

In the sciences, a paper has five-six sections: the abstract; introduction; methods; results; discussion; and sometimes conclusions. Each of these sections has a specific function, and these functions fit papers in computational intelligence just as well as other sciences. Now, computer science in general and computational intelligence in particular is fairly unusual among academic disciplines in that we write full papers for conferences, and give conference papers almost as much weight as journal articles. But this structure evolved to make the contents of papers easier to understand, so it is just as applicable to conference papers as it is to journal articles. The difference is that conference papers are mostly preliminary work, and are shorter, whereas journal articles are longer and report more complete work.

Firstly, the abstract. This is not just a slapped-on piece of text that kinda-sorta says what you did. The abstract is where you summarise the entire paper: what you did, why you did it, what you found. The abstract is the hook by which you draw the reader into your paper, so a bad abstract means people won't read (and cite!) your paper later on.

The introduction sets the scene for your paper: this is where you survey the relevant literature (including all of the introduction stuffing that seems to account for about half of most people's citation count), establish what the problem is, establish what has already been done, and say what you are going to do. If you have any hypotheses or research questions, this is where you lay them out. And every paper should be investigating some hypothesis or research question, even if you don't explicitly state it. The last part of the introduction is where you are setting out for your reader exactly what it is you are trying to achieve in your paper: the earlier parts of the introduction are where you set out why you're doing it.

The methods is where you describe what you did. If you are describing a new technique or algorithm, describe it here, then describe how you evaluated it. If you are using computational intelligence to approach a real-world problem, then describe how you did this. The methods should have enough detail that someone could replicate your work, if they had access to the same data as you did. Don't needlessly repeat well-known algorithms here: I'm quite sick of reviewing conference papers that describe a simple genetic algorithm in their methods section. I know how a simple genetic algorithm works, and so does 99% of the people who are likely to read that paper. If it's well-established, just say which algorithm you used and reference it, that's what references are for.

In the results section you report your results. Since this is a conference paper, you need to focus on the key results. Don't fill half a page or more with a table of numbers! Especially don't give your tables of results captions like "Table of results" - most of your audience will have at least a functional level of reading comprehension, and therefore will already know that they're results. The caption of a table should describe the contents of the table, especially what each column / row heading means, and what the numbers represent. Captions are supposed to be independent of the text, that is,a reader should be able to understand the contents of the table without having to read the entire paper. A large collection of numbers is hard to understand, so in a conference paper it is often better to use a graphical representation of the results than a table. The text of the results describe the results but does not interpret them, so results sections can be quite short. You can describe any analyses of results you did in the results section, but that should probably be left to the discussion.

The discussion in many ways mirrors the introduction, because you are interpreting your results in the context of the literature you cited in the introduction. You are also answering your research questions, identifying any potential shortcomings in your approach, and suggesting future lines of research.In other words, the discussion is where you bring together all of the other sections of your paper. A well-written discussion eliminates the need for a conclusion.

Write succinctly, don't spend a lot of time saying something that can be explained by a reference. When I started writing conference papers in the mid-late 90s, they were limited to four-six pages because conference proceedings were all on paper. Now, conference proceedings are on DVD the page limits tend to be longer, closer to eight pages. But this is the limit, not the recommended number of pages. It's like the speed limit on the roads, the speed limit is the fastest you are allowed to drive, not the minimum speed you should be driving at all times. Just as you adjust your driving speed to the conditions, you should adjust the length of your paper to the material you are presenting: it is better to produce a succinctly-written, clear and to-the-point four page conference paper than it is produce an eight page paper that covers the same work but buries the important points among pages of padding.

Every sentence in a conference papers needs to tell a story, if a sentence doesn't contribute something to the paper, take it out. Avoid common grammatical errors, and don't rely on a spell-checker. Spell-checkers only tell you if a word is incorrectly spelt, it doesn't tell you if it is the wrong word for that sentence (I've seen  quite enough instances of a "pubic announcement", which sounds far ruder than what I assume they meant, which was a "public announcement"). Proof-read the paper at least twice, and if English is not your first language, for goodness sake get a native English speaker to read it. English grammar is bad enough for us native speakers, it has so many traps in it (especially with things like past / present / future tense) that errors are almost inevitable. Grammatical errors jar the reader out of the flow of the work, and if that happens often enough they will lose the thread of the paper and not understand what you are trying to communicate.

Researchers in computational intelligence can do good research, and are able to write good software. There is no reason they should not be able to write good conference papers.


Thursday, February 6, 2014

The problem with academic journals 8

It's been a long time since I last blogged about the problems with academic journals. Several of my old posts described the behaviour of the giant academic publisher Elsevier, specifically trying to buy a law in the US Congress that would virtually ban researchers publishing in open-access journals. This resulted in an enormous backlash against Elsevier, including a boycott that now has more than 14,000 names, culminating in the proposed legislation being dropped.

Unfortunately, Elsevier is back to their old bad behaviour: they have been sending notices to researchers and academic network sites demanding the removal from the web of papers that the researchers' had published in Elsevier journals. While Elsevier may be within their legal rights to do so (since they demand that authors sign over copyright to Elsevier), preventing people from self-archiving papers that they wrote is highly
 detrimental to science. In other words, Elsevier gets the research papers for free (submitted by the authors), they get the quality control for free (done by volunteer reviewers), and the administration of journals for free (done by volunteer editors). Then, they do some basic formatting and proof-reading, demand that the authors surrender all rights to the article, and publish it at an enormous profit.

Some publishers like the IEEE work the same way but allow for self-archiving, that is, they allow authors to post papers they have authored on their own websites for other researchers to access. The IEEE seems to be doing quite well out of this practice, but then the high offices of the IEEE are held by engineers and academics rather than businessmen. Does Elsevier really think that they can get away with this kind of bully-boy behaviour?

There are a couple of Elsevier journals that I've published several papers in, and I still have research that I was going to submit to them. But now I think that It's time for me to find some alternative journals to submit my work to. I'm currently reviewing one article for an Elsevier journal, and I took that task on because a friend asked me to, but after that, I won't review for any Elsevier journals. And I will not, under any circumstances, serve on the editorial board of any Elsevier journals.

Wednesday, February 5, 2014

Neural Networks new articles 2 January - 3 February, 2014

1. Safe semi-supervised learning based on weighted likelihood  
Author(s): Masanori Kawakita, Jun’ichi Takeuchi
   
2. Effects of asymmetric and self coupling on metastable dynamical transient rotating waves in a ring of sigmoidal neurons  
Author(s): Yo Horikawa

3. Kernel learning at the first level of inference  
Author(s): Gavin C. Cawley, Nicola L.C. Talbot
   
4. Convergence behavior of delayed discrete cellular neural network without periodic coefficients
Author(s): Jinling Wang, Haijun Jiang, Cheng Hu, Tianlong Ma
    
5. Generalization performance of Gaussian kernels SVMC based on Markov sampling 
Author(s): Jie Xu, Yuan Yan Tang, Bin Zou, Zongben Xu, Luoqing Li, Yang Lu

6. Assist-as-needed robotic trainer based on reinforcement learning and its application to dart-throwing  
Author(s): Chihiro Obayashi, Tomoya Tamei, Tomohiro Shibata
   
7. Cross-person activity recognition using reduced kernel extreme learning machine 
Author(s): Wan-Yu Deng, Qing-Hua Zheng, Zhong-Min Wang
   
8. Robust head pose estimation via supervised manifold learning  
Author(s): Chao Wang, Xubo Song

9. Synchronization control of memristor-based recurrent neural networks with perturbations  
Author(s): Weiping Wang, Lixiang Li, Haipeng Peng, Jinghua Xiao, Yixian Yang

Tuesday, February 4, 2014

IEEE Transactions on Evolutionary Computation, Volume 18, Number 1, February 2014

1. Guest Editorial: Special Issue on Advances in Multiobjective Evolutionary Algorithms for Data Mining
Author(s): Bandyopadhyay, S. ; Maulik, U. ; Coello, C.A.C. ; Pedrycz, W.
Pages: 1-3

2. A Survey of Multiobjective Evolutionary Algorithms for Data Mining: Part I
Author(s): A. Mukhopadhyay, U. Maulik, S. Bandyopadhyay, and C. A. Coello Coello
Pages: 4-19

3. Survey of Multiobjective Evolutionary Algorithms for Data Mining: Part II
Author(s): A. Mukhopadhyay, U. Maulik, S. Bandyopadhyay, and C. A. Coello Coello
Pages: 20-35

4. Large-Scale Experimental Evaluation of Cluster Representations for Multiobjective Evolutionary Clustering
Author(s): A. Garcia-Piquer, A. Fornells, J. Bacardit, A. Orriols-Puig, and E. Golobardes
Pages: 36-53

5. A New Multiobjective Evolutionary Algorithm for Mining a Reduced Set of Interesting Positive and Negative Quantitative Association Rules
Author(s): D. Martin, A. Rosete, J. Alcala-Fdez, and F. Herrera
Pages: 54-69

6. Population Classification in Fire Evacuation: A Multiobjective Particle Swarm Optimization Approach
Author(s): Y.-J. Zheng, H.-F. Ling, J.-Y. Xue, and S.-Y. Chen
Pages: 70-81

7. Complex Network Clustering by Multiobjective Discrete Particle Swarm Optimization Based on Decomposition
Author(s): M. Gong, Q. Cai, X. Chen, and L. Ma
Pages: 82-97

8. A Novel Graph-Based Estimation of the Distribution Algorithm and Its Extension Using Reinforcement Learning
Author(s): X. Li, S. Mabu, and K. Hirasawa
Pages: 98-113

9. Adaptive Operator Selection With Bandits for a Multiobjective Evolutionary Algorithm Based on Decomposition
Author(s): K. Li, A. Fialho, S. Kwong, and Q. Zhang
Pages: 114-131

10. Performance Metric Ensemble for Multiobjective Evolutionary Algorithms
Author(s): G. G. Yen, and Z. He
Pages: 131-144

Monday, February 3, 2014

IEEE Transactions on Fuzzy Systems, Volume 22, Number 1 February 2014

1. Observer-Based Adaptive Decentralized Fuzzy Fault-Tolerant Control of Nonlinear Large-Scale Systems With Actuator Failures
Author(s): S. Tong, B. Huo, and Y. Li
Pages: 1-15

2. A New Possibilistic Programming Approach For Solving Fuzzy Multiobjective Assignment Problem
Author(s): P. Gupta and M. K. Mehlawat
Pages: 16-34

3. Consistency Measures for Hesitant Fuzzy Linguistic Preference Relations
Author(s): B. Zhu and Z. Xu
Pages: 35-45

4. Probabilistically Weighted OWA Aggregation
Author(s): R. R. Yager and N. Alajlan
Pages: 46-56

5. The Parameter Reduction of the Interval-Valued Fuzzy Soft Sets and Its Related Algorithms
Author(s): X. Ma, H. Qin, N. Sulaiman, T. Herawan, and J.H. Abawajy
Pages: 57-71

6. EFIS—Evolving Fuzzy Image Segmentation
Author(s): A. A. Othman, H. R. Tizhoosh, and F. Khalvati
Pages: 72-82

7. Some Hamacher Aggregation Operators Based on the Interval-Valued Intuitionistic Fuzzy Numbers and Their Application to Group Decision Making
Author(s): P. Liu
Pages: 83-97

8. Fuzzy Clustering With a Modified MRF Energy Function for Change Detection in Synthetic Aperture Radar Images
Author(s): M.Gong, L.Su, M.Jia, and W.Chen
Pages: 98-109

9. Linguistic Prototypes for Data From Eldercare Residents
Author(s): A. Wilbik, J. M. Keller, and J. C. Bezdek
Pages: 110-123

10. Stability and Stabilization of Discrete-Time T–S Fuzzy Systems With Stochastic Perturbation and Time-Varying Delay
Author(s): X. Yang, L. Wu, H.-K .Lam, and X. Su
Pages: 124-138

11. Fault Detection for T–S Fuzzy Systems With Unknown Membership Functions
Author(s): X.-J. Li and G.-H. Yang
Pages: 139-152

12. Sampled-Data Fuzzy Control of Chaotic Systems Based on a T–S Fuzzy Model
Author(s): Z.-G. Wu, P. Shi, H. Su, and J. Chu
Pages: 153-163

13. Adaptive Fuzzy Robust Output Feedback Control of Nonlinear Systems With Unknown Dead Zones Based on a Small-Gain Approach
Author(s): Y. Li, S. Tong, Y. Liu, and T. Li
Pages: 164-176

14. Amount of Information and Attitudinal-Based Method for Ranking Atanassov’s Intuitionistic Fuzzy Values
Author(s): K. Guo
Pages: 177-188

15. H-∞ Fuzzy Control With Randomly Occurring Infinite Distributed Delays and Channel Fadings
Author(s): S. Zhang, Z. Wang, D. Ding, and H. Shu
Pages: 189-200

16. An Agent-Based Fuzzy Collaborative Intelligence Approach for Precise and Accurate Semiconductor Yield Forecasting
Author(s): T. Chen and Y.-C. Wang
Pages: 201-211

17. On Energy-to-Peak Filtering for Nonuniformly Sampled Nonlinear Systems: A Markovian Jump System Approach
Author(s): H. Zhang, Y. Shi, and J. Wang
Pages: 212-222

18. Stability Analysis of Polynomial-Fuzzy-Model-Based Control Systems With Mismatched Premise Membership Functions
Author(s): H.K. Lam and S.-H. Tsai
Pages: 223-229

19. Comments on “Finite-Time H-∞ Fuzzy Control of Nonlinear Jump Systems With Time Delays Via Dynamic Observer-Based State Feedback”
Author(s): Y. Zhang, C. Liu, and H. R. Karimi
Pages: 230

Monday, January 27, 2014

Neural Networks, Volume 51, March 2014

1. Editorial Board  
Pages IFC

Neuroscience

2. Global Mittag-Leffler stability and synchronization of memristor-based fractional-order neural networks  
Pages: 1-8
Author(s): Jiejie Chen, Zhigang Zeng, Ping Jiang
   

Learning Systems

3. Feature selection and multi-kernel learning for sparse representation on a manifold  
Pages: 9-16
Author(s):Jim Jing-Yan Wang, Halima Bensmail, Xin Gao
   
4. Long-term time series prediction using OP-ELM
Pages: 50-56
Author(s):Alexander Grigorievskiy, Yoan Miche, Anne-Mari Ventelä, Eric Séverin, Amaury Lendasse
   
5. Least Square Fast Learning Network for modeling the combustion efficiency of a 300WM coal-fired boiler
Pages: 57-66
Author(s):Guoqiang Li, Peifeng Niu, Huaibao Wang, Yongchao Liu
   

Mathematical and Computational Analysis

6. Neural network for solving convex quadratic bilevel programming problems 
Pages: 17-25
Author(s):Xing He, Chuandong Li, Tingwen Huang, Chaojie Li
   
7. Stability analysis of switched stochastic neural networks with time-varying delays  
Pages: 39-49
Author(s):Xiaotai Wu, Yang Tang, Wenbing Zhang
   
8. Lagrangian support vector regression via unconstrained convex minimization  
Pages: 67-79
Author(s):S. Balasundaram, Deepak Gupta, Kapil
   
9. Periodicity and global exponential stability of generalized Cohen–Grossberg neural networks with discontinuous activations and mixed delays
Pages: 80-95
Author(s):Dongshu Wang, Lihong Huang
   

Engineering and Applications

10. A generalized analog implementation of piecewise linear neuron models using CCII building blocks  
Pages: 26-38
Author(s):Hamid Soleimani, Arash Ahmadi, Mohammad Bavandpour, Ozra Sharifipoor
   
11. Current Events  
Pages I-II


Monday, January 20, 2014

Friday, January 17, 2014

IEEE Transactions on Neural Networks and Learning Systems, Volume 25, Issue 2, February 2014

1. What Are the Differences Between Bayesian Classifiers and Mutual-Information Classifiers?
Author(s): Bao-Gang Hu
Pages: 249 - 264

2. Multikernel Least Mean Square Algorithm
Author(s): Felipe A. Tobar; Sun-Yuan Kung; Danilo P. Mandic
Pages: 265 - 277

3. Quantum Neural Network-Based EEG Filtering for a Brain-Computer Interface
Author(s): Vaibhav Gandhi; Girijesh Prasad; Damien Coyle; Laxmidhar Behera; Thomas Martin McGinnity
Pages: 278 - 288

4. Multiclass From Binary: Expanding One-Versus-All, One-Versus-One and ECOC-Based Approaches
Author(s): Anderson Rocha; Siome Klein Goldenstein
Pages: 289 - 302

5. Short-Term Load and Wind Power Forecasting Using Neural Network-Based Prediction Intervals
Author(s): Hao Quan; Dipti Srinivasan; Abbas Khosravi
Pages: 303 - 315

6. HRLSim: A High Performance Spiking Neural Network Simulator for GPGPU Clusters
Author(s): Kirill Minkovich; Corey M. Thibeault; Michael John O’Brien; Aleksey Nogin; Youngkwan Cho; Narayan Srinivasa
Pages: 316 - 331

7. Sliding-Mode Control Design for Nonlinear Systems Using Probability Density Function Shaping
Author(s): Yu Liu; Hong Wang; Chaohuan Hou
Pages: 332 - 343

8. Nanophotonic Reservoir Computing With Photonic Crystal Cavities to Generate Periodic Patterns
Author(s): Martin Andre Agnes Fiers; Thomas Van Vaerenbergh; Francis Wyffels; David Verstraeten; Benjamin Schrauwen; Joni Dambre; Peter Bienstman
Pages: 344 - 355

9. Efficient Probabilistic Classification Vector Machine With Incremental Basis Function Selection
Author(s): Huanhuan Chen; Peter Tino; Xin Yao
Pages: 356 - 369

10. Zhang Neural Network for Online Solution of Time-Varying Linear Matrix Inequality Aided With an Equality Conversion
Author(s): Dongsheng Guo; Yunong Zhang
Pages: 370 - 382

11. Robust Pole Assignment for Synthesizing Feedback Control Systems Using Recurrent Neural Networks
Author(s): Xinyi Le; Jun Wang
Pages: 383 - 393

12. Efficient Dual Approach to Distance Metric Learning
Author(s): Chunhua Shen; Junae Kim; Fayao Liu; Lei Wang; Anton van den Hengel
Pages: 394 - 406

13. Event-Based Visual Flow
Author(s): Ryad Benosman; Charles Clercq; Xavier Lagorce; Sio-Hoi Ieng; Chiara Bartolozzi
Pages: 407 - 417

14. Decentralized Stabilization for a Class of Continuous-Time Nonlinear Interconnected Systems Using Online Learning Optimal Control Approach
Author(s): Derong Liu; Ding Wang; Hongliang Li
Pages: 418 - 428

15. Novel Adaptive Strategies for Synchronization of Linearly Coupled Neural Networks With Reaction-Diffusion Terms
Author(s): Jin-Liang Wang; Huai-Ning Wu; Lei Guo
Pages: 429 - 440

Thursday, January 16, 2014

IEEE Transactions on Computational Intelligence and AI in Games, Volume 5, Number 4, December 2013

1. A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft
Author(s): Ontanon, S. ; Synnaeve, G. ; Uriarte, A. ; Richoux, F. ; Churchill, D. ; Preuss, M.
Pages: 293-311

2. Repeated Goofspiel: A Game of Pure Strategy
Author(s):Dror, M. ; Kendall, G.
Pages: 312-324

3. A Heuristic-Based Planner and Improved Controller for a Two-Layered Approach for the Game of Billiards
Author(s):Landry, J.-F. ; Dussault, J.-P. ; Mahey, P.
Pages: 325-336

4. Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization
Author(s):Jiang, R. ; Parry, M.L. ; Legg, P.A. ; Chung, D.H.S. ; Griffiths, I.W.
Pages: 337-345

5. Incentive Learning in Monte Carlo Tree Search
Author(s):Kao, K.-Y. ; Wu, I-C. ; Yen, S.-J. ; Shan, Y.-C.
Pages: 346-352

Wednesday, January 15, 2014

Wednesday, January 1, 2014

IEEE Transactions on Neural Networks and Learning Systems: Volume 25, Issue 1, January 2014

1. Guest Editorial: Learning in Nonstationary and Evolving Environments
Author(s): Robi Polikar; Cesare Alippi
Pages: 9 - 11

2. COMPOSE: A Semisupervised Learning Framework for Initially Labeled Nonstationary Streaming Data
Author(s): Karl B. Dyer; Robert Capo; Robi Polikar
Pages: 12 - 26

3. Active Learning With Drifting Streaming Data
Author(s): Indre Zliobaite; Albert Bifet; Bernhard Pfahringer; Geoffrey Holmes
Pages: 27 - 39

4. Online Bayesian Learning With Natural Sequential Prior Distribution
Author(s): Yohei Nakada; Makio Wakahara; Takashi Matsumoto
Pages: 40 - 54

5. PANFIS: A Novel Incremental Learning Machine
Author(s): Mahardhika Pratama; Sreenatha. G. Anavatti; Plamen. P. Angelov; Edwin Lughofer
Pages: 55 - 68

6. PCA Feature Extraction for Change Detection in Multidimensional Unlabeled Data
Author(s): Ludmila I. Kuncheva; William J. Faithfull
Pages: 69 - 80

7. Reacting to Different Types of Concept Drift: The Accuracy Updated Ensemble Algorithm
Author(s): Dariusz Brzezinski; Jerzy Stefanowski
Pages: 81 - 94

8. Mining Recurring Concepts in a Dynamic Feature Space
Author(s): Joao Bartolo Gomes; Mohamed Medhat Gaber; Pedro A. C. Sousa; Ernestina Menasalvas
Pages: 95 - 110

9. Dynamic Learning From Adaptive Neural Network Control of a Class of Nonaffine Nonlinear Systems
Author(s): Shi-Lu Dai; Cong Wang; Min Wang
Pages: 111 - 123

10. Learning in the Model Space for Cognitive Fault Diagnosis
Author(s): Huanhuan Chen; Peter Tino; Ali Rodan; Xin Yao
Pages: 124 - 136

11. Adaptive Approximation for Multiple Sensor Fault Detection and Isolation of Nonlinear Uncertain Systems
Author(s): Vasso Reppa; Marios M. Polycarpou; Christos G. Panayiotou
Pages: 137 - 153

12. Dealing With Concept Drifts in Process Mining
Author(s): R. P. Jagadeesh Chandra Bose; Wil M. P. van der Aalst; Indre Zliobaite; Mykola Pechenizkiy
Pages: 154 - 171

13. Adaptive Convex Combination Approach for the Identification of Improper Quaternion Processes
Author(s): Bukhari Che Ujang; Cyrus Jahanchahi; Clive Cheong Took; Danilo P. Mandic
Pages: 172 - 182

14. Developmental Perception of the Self and Action
Author(s): Ryo Saegusa; Giorgio Metta; Giulio Sandini; Lorenzo Natale
Pages: 183 - 202

15. Linguistic Decision Making for Robot Route Learning
Author(s): Hongmei He; Thomas Martin McGinnity; Sonya Coleman; Bryan Gardiner
Pages: 203 - 215

16. An Interval Type-2 Neural Fuzzy Chip With On-Chip Incremental Learning Ability for Time-Varying Data Sequence Prediction and System Control
Author(s): Chia-Feng Juang; Chi-You Chen
Pages: 216 - 228

17. Learning Geotemporal Nonstationary Failure and Recovery of Power Distribution
Author(s): Yun Wei; Chuanyi Ji; Floyd Galvan; Stephen Couvillon; George Orellana; James Momoh
Pages: 229 - 240

18. Continuous Dynamical Combination of Short and Long-Term Forecasts for Nonstationary Time Series
Author(s): Domingos Savio Pereira Salazar; Paulo Jorge Leitao Adeodato; Adrian Lucena Arnaud
Pages: 241 - 246

Monday, December 23, 2013

Neural Networks Volume 50 Pages 1-182 February 2014

Neural Networks Letters

1. Existence and global exponential stability of periodic solution for high-order discrete-time BAM neural networks 
Pages: 98-109
Author(s): Ancai Zhang, Jianlong Qiu, Jinhua She

2. Cellular computational networks—A scalable architecture for learning the dynamics of large networked systems 
Pages: 120-123
Author(s): Bipul Luitel, Ganesh Kumar Venayagamoorthy

Cognitive Science

3. Supervised orthogonal discriminant subspace projects learning for face recognition  
Pages: 33-46
Author(s): Yu Chen, Xiao-Hong Xu

Learning Systems

4. Direct Kernel Perceptron (DKP): Ultra-fast kernel ELM-based classification with non-iterative closed-form weight calculation 
Pages: 60-71
Author(s): Manuel Fernández-Delgado, Eva Cernadas, Senén Barro, Jorge Ribeiro, José Neves

5. Batch gradient method with smoothing image regularization for training of feedforward neural networks  
Pages: 72-78
Author(s): Wei Wu, Qinwei Fan, Jacek M. Zurada, Jian Wang, Dakun Yang, Yan Liu

6. Compressed classification learning with Markov chain samples 
Pages: 90-97
Author(s): Feilong Cao, Tenghui Dai, Yongquan Zhang, Yuanpeng Tan

7. Semi-supervised learning of class balance under class-prior change by distribution matching  
Pages: 110-119
Author(s): Marthinus Christoffel du Plessis, Masashi Sugiyama

8. Robust support vector machine-trained fuzzy system  
Pages: 154-165
Author(s): Yahya Forghani, Hadi Sadoghi Yazdi

9. Large-scale linear nonparallel support vector machine solver  
Pages: 166-174
Author(s): Yingjie Tian, Yuan Ping

10. Finite time convergent learning law for continuous neural networks  
Pages: 175-182
Author(s): Isaac Chairez
   

Mathematical and Computational Analysis

11. A Bayesian inverse solution using independent component analysis  
Pages: 47-59
Author(s): Jouni Puuronen, Aapo Hyvärinen
   
12. A one-layer recurrent neural network for constrained nonsmooth invex optimization  
Pages: 79-89
Author(s): Guocheng Li, Zheng Yan, Jun Wang
   
13. Pointwise probability reinforcements for robust statistical inference  
Pages: 124-141
Author(s): Benoît Frénay, Michel Verleysen
   
14. A linear recurrent kernel online learning algorithm with sparse updates  
Pages: 142-153
Author(s): Haijin Fan, Qing Song

Engineering and Applications

15. Correcting and combining time series forecasters  
Pages: 1-11
Author(s): Paulo Renato A. Firmino, Paulo S.G. de Mattos Neto, Tiago A.E. Ferreira

16. Hybrid fault diagnosis of nonlinear systems using neural parameter estimators 
Pages: 12-32
Author(s): E. Sobhani-Tehrani, H.A. Talebi, K. Khorasani

Thursday, December 19, 2013

Work-Life Balance

A video of a panel session of two young(ish) professors, talking about work-life balance. I used to work in the same lab as Corey Bradshaw, and have even published with him. He is a straight-speaking person who says what he thinks, so you can be sure that what he says in this session is his honest opinion. That being said, I do have some conflicted feelings about this discussion.



On the one hand, I respect and envy their academic achievements. On the other hand, the sacrifices they have made to get where they are are just terrifying, and strike me as selfish. When Tanya Munro talks about dragging her two tiny babies to a conference, or skipping their end-of-year performance, or both of them talking about leaving their kids at home for the evening again, I can't help but think that that is just so much macho bullsh*t. For me, family comes first, there is no choice. My daughter is smart without being conceited, brave without being reckless, strong without being over-bearing, loving, caring and empathetic, without being clingy. She wouldn't be those things if she didn't have an extended family around her who were fully engaged in her upbringing. I'd rather be a "less-successful" academic, than risk losing what I have with her. She'll grow up soon enough, I can put more energy into my career then. Certainly I could achieve more if I sacrificed more, or if I slept a lot less, but if I worked an 80-hour week, I would die. It's as simple as that. One of the last things my father said to me, just a few days before he died, was "you're not a machine". I refuse to risk depriving my wife of her husband and my daughter of her father.

Another point at which I disagree with Corey is when he mentions telling his post-docs "Start publishing papers or I'm going to have to sack you". I think this is a poor management technique: if someone isn't performing, you as a manager must coach them to lift their game. Management by fear is a poor technique and just breeds resentment. Life may be too short to work with a*holes, but it's also too short to accumulate enemies.

The idea that everything you do should lead to an obvious paper is fine for someone who in only doing research, but personally I couldn't live without undergraduate teaching. I need the surge of energy I get from standing in front of a class and explaining complex concepts. I really love it when someone "gets it", when their face lights up with understanding. Even though I spend most of my time now in management, I'd never take another position where I wasn't teaching.

Finally, everyone's circumstances are different, so you shouldn't compare yourself to others. Tanya Munro may have met her husband during her first year of university, but I met my wife at 28, married her just before turning 30, and had my daughter, finished my PhD, and started my first post-doc at 31. I had problems with my PhD topic, I had health problems, and I had to work to support myself. Now I'm 40 and my career path is finally starting to settle down. I may have achieved less academically than them, but so have most people. What, really, does comparing myself to them achieve? Nothing, except perhaps to make me feel badly about myself.

One thing I do agree with is that you have to find your own balance, your own way. I think I've found mine, and I'm happier for it. The video is well worth the time to view it, if only to gain some perspectives from successful academics.

Wednesday, December 18, 2013

WCCI 2014 Deadline Extension

The deadline for submitting papers to the World Congress on Computational Intelligence (WCCI) 2014 has been extended to the 20th of January, 2014. There will be no further extensions. This conference combines the three major conferences of the IEEE Computational Intelligence Society: The International Joint Conference on Neural Networks (IJCNN); the Congress on Evolutionary Computation (CEC) and the IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). This conference will be held in Beijing, China, July 6-11, 2014.

Monday, December 16, 2013

Reminder: paper submission deadline for EAIS 2014

A reminder that the deadline for submitting papers to the IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS) 2014 is January 15, 2014. This conference will be held in Linz, Austria, June 2-4, 2014.

Friday, December 13, 2013

Reminder: paper submission deadline for IEEE SSCI 2014

A reminder that the deadline for submitting papers to the IEEE Symposium Series on Computational Intelligence (SSCI) 2014 is 15 June 2014. This group of symposia will be held in Orlando, Florida, 9-12 December, 2014.