Weeky Review 22 April 2016

Some interesting links that I Tweeted about in the last week:

1. Difficulties of frequent moves, a hazard for academics: https://www.insidehighered.com/advice/2016/04/15/difficulties-constantly-having-move-academic-essay  Part of why being a postdoc sucks http://computational-intelligence.blogspot.com/2012/09/on-being-post-doc.html
2. Developers guide to Facebook's Messenger chatbot: http://siliconangle.com/blog/2016/04/13/developers-roll-your-own-facebook-messenger-bot-and-what-you-can-do/ 
3. Why it's important for PhD students to blog: https://www.insidehighered.com/blogs/gradhacker/blogging-establish-your-digital-identity  Other ways to establish an online profile: http://computational-intelligence.blogspot.com/2012/04/building-online-presence-as-academic.html 
4. My final paper for IJCNN 2016: "Sleep Learning and Max-Min Aggregation of Evolving Connectionist Systems" http://mike.watts.net.nz/SleepLearningMaxMinAggregationECoS.pdf 
5. Machine learning detects 85% of network attacks: http://www.theregister.co.uk/2016/04/18/ai_bot_spots_hacking_attacks/
6. Paper on the AI^2 machine-learning based network intrusion detection system: https://people.csail.mit.edu/kalyan/AI2_Paper.pdf 
7. Using deep learning to detect cancer cells in blood samples: http://newsroom.ucla.edu/releases/microscope-uses-artificial-intelligence-to-find-cancer-cells-more-efficiently 
8. Recognising hand-written Japanese text with deep learning: http://www.bloomberg.com/news/articles/2016-04-13/artificial-intelligence-s-next-phase-sooner-and-more-accessible-for-everyone 
9. A list of deep learning tutorials and resources: http://www.datasciencecentral.com/profiles/blogs/11-deep-learning-articles-tutorials-and-resources 
10. Introduction to deep learning for chatbots: http://www.kdnuggets.com/2016/04/deep-learning-chatbots-part-1.html
11. Gender diversity in AI: http://motherboard.vice.com/en_au/read/can-ai-help-gender-diversity-help-ai
12. List of 15 machine learning frameworks: http://www.kdnuggets.com/2016/04/top-15-frameworks-machine-learning-experts.html 
13. Yet another article on the AI^2 system: http://techemergence.com/an-ai-cybersecurity-system-may-detect-attacks-with-85-percent-accuracy/ Machine learning in security isn't that new, it's been done for years.
14. Adding on-board intelligence to thermal cameras: http://www.theverge.com/2016/4/19/11459182/flir-movidius-boson-thermal-camera-computer-vision
15. An ontology of machine learning methods: http://www.datasciencecentral.com/profiles/blogs/machine-learning-ontology 
16. Guide to data analysis in Python: http://www.kdnuggets.com/2016/04/datacamp-learning-python-data-analysis-data-science.html 
17. Randomized Forest ensemble method: http://www.datasciencecentral.com/profiles/blogs/random-ized-forest-thought-vectors-to-build-a-new-class-of Not so new as the author of the article says it is.
18. Some basic advice on getting published in journals: https://www.insidehighered.com/advice/2016/04/21/advice-getting-published-scholarly-journal-essay 
19. How machine learning is needed in computer security: http://www.datanami.com/2016/04/21/machine-learning-can-applied-cyber-security/ 
20. Has this startup made an AI that passes the Turing test? http://techemergence.com/x-ai-says-their-ai-passed-the-turing-test/ 
21. The incredible growth of R: http://www.techrepublic.com/article/exponential-growth-of-rs-open-source-community-threatens-commercial-competitors/

Weekly Review 15 April 2016

Some interesting links that I Tweeted about in the last week:

1. How to fool deep learning networks: http://www.kdnuggets.com/2016/04/tricking-deep-learning.html
2. AI is going to change your job, but not replace it: http://www.information-age.com/it-management/skills-training-and-leadership/123461209/why-machine-learning-will-impact-not-take-your-job 
3. Using AI to help treat diabetes: https://www.devex.com/news/using-artificial-intelligence-to-revolutionize-diabetes-treatment-87989
4. What's been happening with IBM's Watson: http://hothardware.com/news/ibms-watson-cognitive-ai-platform-evolves-senses-feelings-and-dances-gangnam-style
5. Should universities be employing PhDs as administrators? http://schoolofdoubt.com/2016/04/10/universities-should-be-employing-surplus-phds-as-administrative-staff/ 
6. Analysing ancient texts using machine learning: http://gizmodo.com/artificial-intelligence-sheds-new-light-on-the-origins-1769736018
7. Predicting customer behaviour with machine learning: http://www.datasciencecentral.com/profiles/blogs/using-machine-learning-to-predict-customer-behaviour 
8. Are fears brought about from sci-fi holding back AI research? https://www.theguardian.com/technology/2016/apr/12/brave-new-world-sci-fi-fears-hold-back-progress-of-ai-warns-expert
9. Some deep learning / machine learning / ANN terms explained: http://www.datasciencecentral.com/profiles/blogs/10-deep-learning-terms-explained-in-simple-english 
10. How AI is creeping into business and our lives: http://www.nzherald.co.nz/opinion/news/article.cfm?c_id=466&objectid=11621278 
11. Deep learning on GPU is racing ahead: http://www.datanami.com/2016/04/13/gpu-powered-deep-learning-emerges-carry-big-data-torch-forward/ 
12. Are chatbots trustworthy? http://www.computerworld.com/article/3055713/social-media/will-companys-trust-their-communications-to-a-i-chatbots.html 
13. Google has updated TensorFlow, can now be distributed over multiple devices: https://www.theguardian.com/technology/2016/apr/13/google-updates-tensorflow-open-source-artificial-intelligence
14. What developers need to know about machine learning: http://www.kdnuggets.com/2016/04/developers-need-know-about-machine-learning.html 
15. Data mining people's personalities for targeted political advertising: https://www.technologyreview.com/s/601214/data-mining-your-psyche/#/set/id/601281/
16. Algorithmically generating art with ArtBots: https://www.theguardian.com/technology/2016/apr/15/move-over-chatbots-meet-the-artbots
17. AI is helping the visually-impaired perceive the world: http://techemergence.com/unseen-ways-ai-is-making-the-world-a-better-place/

Weekly Review 8 April 2016

Some interesting links that I Tweeted about in the last week:

1. Assisting dieting with machine learning: http://spectrum.ieee.org/the-human-os/biomedical/diagnostics/machine-learning-for-easier-dieting
2. Microsoft is open sourcing their chatbot software: http://www.theguardian.com/technology/2016/mar/31/now-anyone-can-build-own-version-microsoft-racist-sexist-chatbot-tay
3. Using deep learning to search Shutterstock's image collection: http://www.kdnuggets.com/2016/04/shutterstock-deep-learning-change-language-search.html
4. Being an academic is hard. Becoming one is harder. So much of an academic career is a test of endurance. http://muckyphd.blogspot.co.nz/2016/03/coming-to-terms-with-academic-failure.html 
5. The Cyc project is still going - and finding applications in medicine: http://techemergence.com/a-30-year-old-ai-project-hits-the-market/ 
6. Microsoft launches Cognitive Services http://venturebeat.com/2016/03/30/microsoft-cognitive-services-project-oxford/  22 APIs on computer vision, speaker recognition, etc: https://www.microsoft.com/cognitive-services 
7. On the exploitation in academic publishing: https://medium.com/age-of-awareness/academic-publishing-is-a-goddamned-exploitative-farce-75930d3ce3d0#.95kkkly94
8. C4.5, SVM & APRIORI algorithms explained: http://dataconomy.com/top-3-algorithms-plain-english/
9. Dieting and machine learning: http://motherboard.vice.com/en_au/read/how-machine-learning-dieting-app-health 
10. How to make AIs sound more like humans: http://www.computerworld.com/article/3051174/big-data/what-will-it-take-to-make-ai-sound-more-human.html
11. Combining human experts with machine learning for cybersecurity: http://www.techrepublic.com/article/how-one-ai-security-system-combines-humans-and-machine-learning-to-detect-cyberthreats/
12. Google's machine learning for developers: http://www.techrepublic.com/article/how-developers-can-take-advantage-of-machine-learning-on-google-cloud-platform/
13. The job market for new PhDs is getting smaller and smaller: https://www.insidehighered.com/news/2016/04/04/new-data-show-tightening-phd-job-market-across-disciplines
14. AI systems in journalism, now getting as good as human writers: http://www.theguardian.com/media/2016/apr/03/artificla-intelligence-robot-reporter-pulitzer-prize 
15. Deep learning for smart cities: http://www.datasciencecentral.com/profiles/blogs/deep-learning-applications-for-smart-cities 
16. Some machine learning "trade secrets" http://www.datasciencecentral.com/profiles/blogs/machine-learning-few-rarely-shared-trade-secrets 
17. My h-index just hit 16 - will it stay there this time? https://scholar.google.com/citations?user=Z29KBKYAAAAJ 
18. The applications of AI in finance: http://techemergence.com/dont-fear-ai-in-finance/ 
19. Facebook's AI for automatically describing images: http://www.techrepublic.com/article/facebook-is-using-ai-to-help-blind-people-see-the-photos-in-their-newsfeed/ 
20. Teaching experience is important for post-grads. Co-teaching is one approach to getting it: https://www.insidehighered.com/advice/2016/04/05/advantages-co-teaching-graduate-students-essay 
21. Microsoft announces its Cognitive Services and Bot Framework: https://blogs.technet.microsoft.com/machinelearning/2016/03/30/from-analytical-applications-to-intelligent-solutions/ 
22. Nvidia launches a 15-billion transistor chip for deep learning: http://venturebeat.com/2016/04/05/nvidia-creates-a-15b-transistor-chip-for-deep-learning/ 
23. Another article on Nvidia's 15 billion transistor chip for deep learning: https://www.technologyreview.com/s/601195/a-2-billion-chip-to-accelerate-artificial-intelligence/#/set/id/601193/ 
24. How Livermore National Laboratory will test IBM's neuromorphic chips: http://spectrum.ieee.org/tech-talk/computing/hardware/how-livermore-scientists-will-put-ibms-brain-inspired-chips-to-the-test 
25. Applying deep learning to the Internet of Things using H20: http://www.kdnuggets.com/2016/04/deep-learning-iot-h2o.html
26. Some tips and tricks for using deep neural networks: http://www.datasciencecentral.com/profiles/blogs/must-know-tips-tricks-in-deep-neural-networks 
27. AI in the military: http://www.techrepublic.com/article/how-ai-powered-robots-will-protect-the-networked-soldier/
28. Machine learning in business revenue forecasting: http://www.datasciencecentral.com/profiles/blogs/what-s-a-cfo-s-biggest-fear-and-how-can-machine-learning-help 
29. The basics of GPU computing: http://www.kdnuggets.com/2016/04/basics-gpu-computing-data-scientists.html 
30. A description of deep learning stochastic depth networks: http://www.kdnuggets.com/2016/04/stochastic-depth-networks-accelerate-deep-learning.html

Neural Networks, Volume 77, Pages 1-126, May 2016

1) Image and geometry processing with Oriented and Scalable Map  
Author(s): Hao Hua
Pages: 1-6

2) Noise further expresses exponential decay for globally exponentially stable time-varying delayed neural networks  
Author(s): Song Zhu, Qiqi Yang, Yi Shen
Pages: 7-13

3) A Fast SVD-Hidden-nodes based Extreme Learning Machine for Large-Scale Data Analytics  
Author(s): Wan-Yu Deng, Zuo Bai, Guang-Bin Huang, Qing-Hua Zheng
Pages: 14-28

4) Neuromorphic VLSI realization of the hippocampal formation  
Author(s): Anu Aggarwal
Pages: 29-40

5) Synchronization for an array of neural networks with hybrid coupling by a novel pinning control strategy  
Author(s): Dawei Gong, Frank L. Lewis, Liping Wang, Ke Xu
Pages: 41-50

6) Analysis of global image stability and global asymptotical periodicity for a class of fractional-order complex-valued neural networks with time varying delays  
Author(s): R. Rakkiyappan, R. Sivaranjani, G. Velmurugan, Jinde Cao
Pages: 51-69

7) State estimation for a class of artificial neural networks with stochastically corrupted measurements under Round-Robin protocol  
Author(s): Yuqiang Luo, Zidong Wang, Guoliang Wei, Fuad E. Alsaadi, Tasawar Hayat
Pages: 70-79

8) Global exponential stability of neural networks with time-varying delay based on free-matrix-based integral inequality  
Author(s): Yong He, Meng-Di Ji, Chuan-Ke Zhang, Min Wu
Pages: 80-86

9) Towards holographic “brain” memory based on randomization and Walsh–Hadamard transformation  
Author(s): Daniel Berend, Shlomi Dolev, Sergey Frenkel, Ariel Hanemann
Pages: 87-94

10) Function approximation in inhibitory networks  
Author(s): Bryan Tripp, Chris Eliasmith
Pages: 95-106

11) Tensor SOM and tensor GTM: Nonlinear tensor analysis by topographic mappings  
Author(s): Tohru Iwasaki, Tetsuo Furukawa
Pages: 107-125

IEEE Transactions on Neural Networks and Learning Systems, Volume 27, Issue 4, April 2016

1. A Simple Method for Solving the SVM Regularization Path for Semidefinite Kernels
Author(s): Christopher G. Sentelle; Georgios C. Anagnostopoulos; Michael Georgiopoulos
Page(s): 709 - 722

2. Approximate Orthogonal Sparse Embedding for Dimensionality Reduction
Author(s): Zhihui Lai; Wai Keung Wong; Yong Xu; Jian Yang; David Zhang
Page(s): 723 - 735

3. Bayesian Robust Tensor Factorization for Incomplete Multiway Data
Author(s): Qibin Zhao; Guoxu Zhou; Liqing Zhang; Andrzej Cichocki; Shun-Ichi Amari
Page(s): 736 - 748

4. Pinning Control Strategies for Synchronization of Linearly Coupled Neural Networks With Reaction–Diffusion Terms
Author(s): Jin-Liang Wang; Huai-Ning Wu; Tingwen Huang; Shun-Yan Ren
Page(s): 749 - 761

5. Finite-Time Consensus for Multiagent Systems With Cooperative and Antagonistic Interactions
Author(s): Deyuan Meng; Yingmin Jia; Junping Du
Page(s): 762 - 770

6. Kernel-Based Least Squares Temporal Difference With Gradient Correction
Author(s): Tianheng Song; Dazi Li; Liulin Cao; Kotaro Hirasawa
Page(s): 771 - 782

7. Sparse LSSVM in Primal Using Cholesky Factorization for Large-Scale Problems
Author(s): Shuisheng Zhou
Page(s): 783 - 795

8. Effective Discriminative Feature Selection With Nontrivial Solution
Author(s): Hong Tao; Chenping Hou; Feiping Nie; Yuanyuan Jiao; Dongyun Yi
Page(s): 796 - 808

9. Extreme Learning Machine for Multilayer Perceptron
Author(s): Jiexiong Tang; Chenwei Deng; Guang-Bin Huang
Page(s): 809 - 821

10. Robust Gradient Learning With Applications
Author(s): Yunlong Feng; Yuning Yang; Johan A. K. Suykens
Page(s): 822 - 835

11. An Asynchronous Recurrent Network of Cellular Automaton-Based Neurons and Its Reproduction of Spiking Neural Network Activities
Author(s): Takashi Matsubara; Hiroyuki Torikai
Page(s): 836 - 852

12. Finite-Time Consensus of Multiagent Systems With a Switching Protocol
Author(s): Xiaoyang Liu; James Lam; Wenwu Yu; Guanrong Chen
Page(s): 853 - 862

13. Objective Function and Learning Algorithm for the General Node Fault Situation
Author(s): Yi Xiao; Rui-Bin Feng; Chi-Sing Leung; John Sum
Page(s): 863 - 874

14. Sparse Principal Component Analysis via Rotation and Truncation
Author(s): Zhenfang Hu; Gang Pan; Yueming Wang; Zhaohui Wu
Page(s): 875 - 890

15. Low-Discrepancy Points for Deterministic Assignment of Hidden Weights in Extreme Learning Machines
Author(s): Cristiano Cervellera; Danilo Macciò
Page(s): 891 - 896

16. Asymptotic Normality of the Maximum Pseudolikelihood Estimator for Fully Visible Boltzmann Machines
Author(s): Hien D. Nguyen; Ian A. Wood
Page(s): 897 - 902

17. Mixed H-Infinity and Passive Filtering for Discrete Fuzzy Neural Networks With Stochastic Jumps and Time Delays
Author(s): Peng Shi; Yingqi Zhang; Mohammed Chadli; Ramesh K. Agarwal
Page(s): 903 - 909

Weekly Review 1 April 2016

Some interesting links that I Tweeted about in the last week:

1. Valuing the AI market for 2016 http://techemergence.com/valuing-the-artificial-intelligence-market-2016-and-beyond/?utm_source=facebook&utm_medium=paid-promoted-post&utm_term=ai-market-size&utm_content=180last&utm_campaign=blog
2. Using machine learning to improve automatic speech recognition: http://spectrum.ieee.org/tech-talk/computing/software/machines-just-got-better-at-lip-reading
3. Resistive Processing Units to accelerate training in deep learning neural networks: http://www.tomshardware.com/news/ibm-chip-30000x-ai-speedup,31484.html
4. Paper on Resistive Processing Units for deep learning: http://arxiv.org/abs/1603.07341
5. Computers don't cause a net decrease in job numbers, but do increase inequality, with the lowest-paid hit hardest: https://hbr.org/2016/03/computers-dont-kill-jobs-but-do-increase-inequality
6. What I like to call "avoiding work by doing work" - doing small tasks to avoid doing larger tasks: https://www.insidehighered.com/blogs/gradhacker/two-one-deal-killing-boredom-procrastination 
7. UK's Wellcome Trust wants research they fund published in open access journals: http://www.theregister.co.uk/2016/03/26/sick_of_costly_research_journals/ 
8. Robots learning to pick things up using deep learning neural networks: http://spectrum.ieee.org/automaton/robotics/artificial-intelligence/google-large-scale-robotic-grasping-project 
9. This article seems to be arguing that it's better to get "off the shelf" machine learning than to develop your own: http://www.kdnuggets.com/2016/03/dont-buy-machine-learning.html 
10. AlphaGo and the declining advantage of big companies: https://hbr.org/2016/03/alphago-and-the-declining-advantage-of-big-companies?utm_source=twitter&utm_medium=social&utm_campaign=harvardbiz 
11. Lots of companies getting into AI now: http://www.informationweek.com/big-data/big-data-analytics/google-loves-machine-learning-cloudera-acquires-startup-big-data-roundup/d/d-id/1324845
12. AI hits the mainstream: https://www.technologyreview.com/s/600986/ai-hits-the-mainstream/
13. AI is getting big in Silicon Valley: http://www.nytimes.com/2016/03/28/technology/silicon-valley-looks-to-artificial-intelligence-for-the-next-big-thing.html?mwrsm=Twitter 
14. Note to post-grads: don't EVER use graphs like these in your dissertation, I will fail you! http://www.buzzfeed.com/katienotopoulos/graphs-that-lied-to-us#.scqWJelqk 
15. Neural network chip could bring convolutional neural networks to mobile devices: http://spectrum.ieee.org/computing/embedded-systems/bringing-big-neural-networks-to-selfdriving-cars-smartphones-and-drones 
16. One step to become a machine learning expert: http://www.kdnuggets.com/2016/03/become-machine-learning-expert-one-simple-step.html 
17. Building models is a skill, and like every other skill it must be practiced to be mastered: http://www.kdnuggets.com/2016/03/become-machine-learning-expert-one-simple-step.html 
18. How to tell if the performance of two classifiers is statistically significantly different: http://www.kdnuggets.com/2016/03/statistical-significance-two-classifiers-performance-difference.html
19. The fortunate failure of Microsoft's Tay: http://www.businessinsider.de/why-microsofts-chatbot-tay-should-make-us-look-at-ourselves?r=US&IR=T&utm_content=buffer919c9&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer 
20. Some people would rather have a computer for a boss than a human: http://motherboard.vice.com/en_au/read/a-third-of-young-canadians-would-prefer-a-robot-boss
21. Is the next step for Google DeepMind playing poker? http://www.theguardian.com/technology/2016/mar/30/deepmind-poker-alphago-computer-casino 
22. Machine learning in signature detection for cybersecurity: http://www.darkreading.com/attacks-breaches/machine-learning-in-security-good-and-bad-news-about-signatures/a/d-id/1324888 
23. Google hypes machine learning to sell its cloud computing platform: http://www.informationweek.com/cloud/infrastructure-as-a-service/google-pumps-up-cloud-platform-with-machine-learning/d/d-id/1324822 
24. I'm sure I read / reviewed a paper about this - density-based unsupervised clustering: http://www.datasciencecentral.com/profiles/blogs/variance-clustering-test-of-hypotheses-and-density-estimation-rev 
25. Fighting China's - and especially Beijing's - smog with machine learning: https://www.technologyreview.com/s/600993/can-machine-learning-help-lift-chinas-smog/
26. Low-power, neuromorphic chips being applied in the US nuclear industry: http://www.computerworld.com/article/3049380/big-data/this-brain-inspired-supercomputer-will-explore-deep-learning-for-the-us-nuclear-program.html 
27. Machine learning in signature detection for cybersecurity part 2: http://www.darkreading.com/attacks-breaches/machine-learning-in-security-seeing-the-nth-dimension-in-signatures-/a/d-id/1324889 
28. How Google plans to solve Artificial General Intelligence: https://www.technologyreview.com/s/601139/how-google-plans-to-solve-artificial-intelligence/ 
29. Avoiding complexity in machine learning: http://www.kdnuggets.com/2016/03/avoiding-complexity-machine-learning-problems.html 
30. Artificial Intelligence still works best when AI is paired with humans: https://www.technologyreview.com/s/600989/man-and-machine/
31. Would the health care app space be a good place to apply machine learning? http://spectrum.ieee.org/the-human-os/biomedical/devices/ahead-of-apple-carekits-debut-physicians-still-skeptical-of-health-apps 
32. How Baidu is using AI, especially deep learning: https://www.technologyreview.com/s/600988/how-ai-is-feeding-chinas-internet-dragon/ 
33. I wonder if this approach could be used to generate real estate listings? They're not that different from clickbait: http://larseidnes.com/2015/10/13/auto-generating-clickbait-with-recurrent-neural-networks/

 

IEEE Transactions on Fuzzy Systems, Volume 24, Number 2, April 2016

1) On Atanassov's Intuitionistic Fuzzy Sets in the Complex Plane and the Field of Intuitionistic Fuzzy Numbers
Author(s): L. Zhou
Page(s): 253 - 259

2) Preaggregation Functions: Construction and an Application
Author(s): G. Lucca; J. A. Sanz; G. P. Dimuro; B. Bedregal; R. Mesiar; A. Kolesárová; H. Bustince
Page(s): 260 - 272

3) Modified AHP for Gene Selection and Cancer Classification Using Type-2 Fuzzy Logic
Author(s): T. Nguyen; S. Nahavandi
Page(s): 273 - 287

4) Answering Approximate Queries Over XML Data
Author(s): J. Liu; D. L. Yan
Page(s): 288 - 305

5) A Linear General Type-2 Fuzzy-Logic-Based Computing With Words Approach for Realizing an Ambient Intelligent Platform for Cooking Recipe Recommendation
Author(s): A. Bilgin; H. Hagras; J. van Helvert; D. Alghazzawi
Page(s): 306 - 329

6) Adaptive Quantized Controller Design Via Backstepping and Stochastic Small-Gain Approach
Author(s): F. Wang; Z. Liu; Y. Zhang; C. L. P. Chen
Page(s): 330 - 343

7) Estimation of a Fuzzy Regression Model Using Fuzzy Distances
Author(s): A. F. Roldán López de Hierro; J. Martínez-Moreno; C. Aguilar-Peña; C. R. L. de Hierro
Page(s): 344 - 359

8) Local Divergences for Atanassov Intuitionistic Fuzzy Sets
Author(s): I. Montes; V. Janiš; N. R. Pal; S. Montes
Page(s): 360 - 373

9) Ant-Inspired Fuzzily Deceptive Robots
Author(s): M. Kouzehgar; M. Badamchizadeh; M. R. Feizi-Derakhshi
Page(s): 374 - 387

10) Fuzzy-Model-Based Reliable Static Output Feedback maths\cr{H}_{\infty } Control of Nonlinear Hyperbolic PDE Systems
Author(s): J. Qiu; S. X. Ding; H. Gao; S. Yin
Page(s): 388 - 400

11) DOB Fuzzy Controller Design for Non-Gaussian Stochastic Distribution Systems Using Two-Step Fuzzy Identification
Author(s): Y. Yi; W. X. Zheng; C. Sun; L. Guo
Page(s): 401 - 418

12) A Dynamic Multiagent Genetic Algorithm for Gene Regulatory Network Reconstruction Based on Fuzzy Cognitive Maps
Author(s): J. Liu; Y. Chi; C. Zhu
Page(s): 419 - 431

13) Dissipativity Analysis for Discrete Time-Delay Fuzzy Neural Networks With Markovian Jumps
Author(s): Y. Zhang; P. Shi; R. K. Agarwal; Y. Shi
Page(s): 432 - 443

14) Cooperative Games and Coalition Cohesion Indices: The Choquet–Owen Value
Author(s): M. G. Fiestras-Janeiro; J. M. Gallardo; A. Jiménez-Losada; M. A. Mosquera
Page(s): 444 - 455

15) Fuzzy Clustering in a Complex Network Based on Content Relevance and Link Structures
Author(s): L. Hu; K. C. C. Chan
Page(s): 456 - 470

16) Cooperative Fuzzy Model-Predictive Control
Author(s): M. Killian; B. Mayer; A. Schirrer; M. Kozek
Page(s): 471 - 482

17) Fuzzy Metric Space Induced by Intuitionistic Fuzzy Points and its Application to the Orienteering Problem
Author(s): M. Verma; K. K. Shukla
Page(s): 483 - 488

18) Designing Fuzzy Sets With the Use of the Parametric Principle of Justifiable Granularity
Author(s): W. Pedrycz; X. Wang
Page(s): 489 - 496

19) Unified Representation of Sets of Heterogeneous Markov Transition Matrices
Author(s): M. E. Y. Boudaren; W. Pieczynski
Page(s): 497 - 503

IEEE Transactions on Evolutionary Computation, Volume 20, Number 2, April 2016

1) A Tunable Generator of Instances of Permutation-Based Combinatorial Optimization Problems
Author(s): L. Hernando; A. Mendiburu; J. A. Lozano
Page(s): 165 - 179

2) Balancing Convergence and Diversity in Decomposition-Based Many-Objective Optimizers
Author(s): Y. Yuan; H. Xu; B. Wang; B. Zhang; X. Yao
Page(s): 180 - 198

3) Solving Bilevel Multicriterion Optimization Problems With Lower Level Decision Uncertainty
Author(s): A. Sinha; P. Malo; K. Deb; P. Korhonen; J. Wallenius
Page(s): 199 - 217

4) Leveraged Neighborhood Restructuring in Cultural Algorithms for Solving Real-World Numerical Optimization Problems
Author(s): M. Z. Ali; P. N. Suganthan; R. G. Reynolds; A. F. Al-Badarneh
Page(s): 218 - 231

5) Adaptive Cross-Generation Differential Evolution Operators for Multiobjective Optimization
Author(s): X. Qiu; J. X. Xu; K. C. Tan; H. A. Abbass
Page(s): 232 - 244

6) Simple Probabilistic Population-Based Optimization
Author(s): Y. C. Lin; M. Clauß; M. Middendorf
Page(s): 245 - 262

7) Tunably Rugged Landscapes With Known Maximum and Minimum
Author(s): N. Manukyan; M. J. Eppstein; J. S. Buzas
Page(s): 263 - 274

8) A Multiobjective Evolutionary Algorithm Based on Decision Variable Analyses for Multiobjective  
Author(s): Optimization Problems With Large-Scale Variables
X. Ma; F. Liu; Y. Qi; X. Wang; L. Li; L. Jiao; M. Yin; M. Gong
Page(s): 275 - 298

9) Generalization of Pareto-Optimality for Many-Objective Evolutionary Optimization
Author(s): C. Zhu; L. Xu; E. D. Goodman
Page(s): 299 - 315

10) Average Convergence Rate of Evolutionary Algorithms
Author(s): J. He; G. Lin
Page(s): 316 - 321

Weekly Review 25 March 2016

Some interesting links that I Tweeted about in the last week:

1. Fundamentals of neural networks: http://www.analyticsvidhya.com/blog/2016/03/introduction-deep-learning-fundamentals-neural-networks/
2. Why AlphaGo is not the be-all and end-all of AI: http://www.kdnuggets.com/2016/03/alphago-not-solution-ai.html
3. Biases in facial recognition: http://motherboard.vice.com/en_au/read/the-inherent-bias-of-facial-recognition
4. Tips for using deep-learning neural networks: http://www.kdnuggets.com/2016/03/must-know-tips-deep-learning-part-1.html
5. An AI chatbot to help psychologically traumatised refugees: http://www.theguardian.com/technology/2016/mar/22/karim-the-ai-delivers-psychological-support-to-syrian-refugees
6. Gauging someone's mood from their voice, using deep learning neural networks: https://thestack.com/world/2016/03/21/mood-mining-researchers-propose-app-to-judge-your-long-term-state-of-mind-from-your-voice/ 
7. Using machine learning for artificial empathy in marketing: http://motherboard.vice.com/en_au/read/how-companies-will-use-artificial-empathy-to-sell-you-more-shit 
8. Diagnosing heart disease from MRI images using convolutional neural networks: http://irakorshunova.github.io/2016/03/15/heart.html 
9. The future of AI in law: http://dataconomy.com/ai-future-law-lawyers-know/  If this lowers cost of access to legal representation, that will be a good thing
10. Applying machine learning to choosing and predicting the quality of wine: http://dataconomy.com/the-perfect-pairing-machine-learning-and-wine/ 
11. Getting started in R: http://www.kdnuggets.com/2016/03/datacamp-r-learning-path-7-steps.html
12. More tips for using deep learning neural networks: http://www.kdnuggets.com/2016/03/must-know-tips-deep-learning-part-2.html
13. Converting numerical variables to categorical variables: http://www.datasciencecentral.com/profiles/blogs/how-to-bin-or-convert-numerical-variables-to-categorical
14. Why regulators are unprepared for AI: http://www.slate.com/articles/technology/future_tense/2016/03/regulators_are_underprepared_for_artificial_intelligence_they_could_learn.html
15. My seminar on what I look for when examining a post-graduate (especially doctoral) thesis: https://drive.google.com/file/d/0B0vCoxTCjd34SW1JRmZpYVpXUDQ/view?usp=sharing 
16. Google opens access to its deep neural network-based speech recognition API: http://techcrunch.com/2016/03/23/google-opens-access-to-its-speech-recognition-api-going-head-to-head-with-nuance/
17. Japanese AI wrote a short novel, and it passed the first round of a literary competition: http://www.digitaltrends.com/cool-tech/japanese-ai-writes-novel-passes-first-round-nationanl-literary-prize/

Weekly Review 20 March 2016

Some interesting links that I Tweeted about in the last week:

1. So, computers are now better at Go, than the best human player: http://www.nature.com/news/the-go-files-ai-computer-clinches-victory-against-go-champion-1.19553
2. 7 situations where more data isn't necessarily better: http://www.datasciencecentral.com/profiles/blogs/7-cases-where-big-data-isn-t-better 
3. Human vs AlphaGo now 1-3 in favour of the machine: http://www.theguardian.com/world/2016/mar/13/go-humans-lee-sedol-scores-first-victory-against-supercomputer
4. Follow the instructions when applying for a job: https://www.insidehighered.com/advice/2016/03/14/importance-following-directions-when-you-apply-jobs-essay And ecologists, don't ask me for a postdoc position, I'm comp sci!
5. 4-1 to the machine: http://spectrum.ieee.org/tech-talk/computing/networks/alphago-wins-match-against-top-go-player 
6. US companies are buying-up British AI companies: http://motherboard.vice.com/en_au/read/why-the-us-is-buying-up-so-many-uk-artificial-intelligence-companies 
7. Should all research papers be free? http://www.nytimes.com/2016/03/13/opinion/sunday/should-all-research-papers-be-free.html Yes, they should!
8. Call for Papers: ICTAI 2016: The 28th International Conference on Tools with Artificial Intelligence, November... http://bit.ly/1YZfJN0
9. List of resources on machine learning: http://www.datasciencecentral.com/profiles/blogs/43-new-external-machine-learning-resources-and-updated-articles
10. Human-assisted machine learning: http://www.datanami.com/2016/03/17/unleashing-artificial-intelligence-human-assisted-machine-learning/ I seem to remember Arthur C. Clarke writing about something similar 30 years ago.
11. AI needs to work with humans, not against them: http://www.datanami.com/2016/03/17/unleashing-artificial-intelligence-human-assisted-machine-learning/
12. I wonder if these robo-advisors use machine learning or other AI technology? https://thestack.com/world/2016/03/16/rbs-cuts-hundreds-of-jobs-as-fca-approves-robo-advisers/
13. A bit depressing, but not terribly surprising: http://qz.com/373436/373436/ 
14. "Preferred reviewers"?? Not the best idea ever: https://methodsblog.wordpress.com/2015/10/15/preferred-reviewers/
15. Fundamentals of deep learning: http://www.analyticsvidhya.com/blog/2016/03/introduction-deep-learning-fundamentals-neural-networks/
16. Applying Sun Tzu's Art of War to software development: http://www.datasciencecentral.com/profiles/blogs/the-art-of-war-applied-to-software-development
17. South Korea is investing big in AI research: http://www.nature.com/news/south-korea-trumpets-860-million-ai-fund-after-alphago-shock-1.19595
18. 80 % of Chinese workers think AI will replace them. Conversely, only 39 % of German workers think the same: http://qz.com/642741/the-workers-in-these-countries-believe-ai-and-robots-will-replace-them/

IEEE Transactions on Computational Intelligence and AI in Games, Volume8, Issue 1, March 2016

1) Predicting Dominance Rankings for Score-Based Games
Author(s): S. Samothrakis; D. Perez; S. M. Lucas; P. Rohlfshagen
Page(s): 1 - 12

2) Solving a Complex Language Game by Using Knowledge-Based Word Associations Discovery
Author(s): P. Basile; M. de Gemmis; P. Lops; G. Semeraro
Page(s): 13 - 26

3) Extending Real-Time Challenge Balancing to Multiplayer Games: A Study on Eco-Driving
Author(s): H. Prendinger; K. Puntumapon; M. Madruga
Page(s): 27 - 32

4) Online Adaptable Learning Rates for the Game Connect-4
Author(s): S. Bagheri; M. Thill; P. Koch; W. Konen
Page(s): 33 - 42

5) Intelligent Game Engine for Rehabilitation (IGER)
Author(s): M. Pirovano; R. Mainetti; G. Baud-Bovy; P. L. Lanzi; N. A. Borghese
Page(s): 43 - 55

6) Reinforcement Learning in Video Games Using Nearest Neighbor Interpolation and Metric Learning
Author(s): M. S. Emigh; E. G. Kriminger; A. J. Brockmeier; J. C. Príncipe; P. M. Pardalos
Page(s): 56 - 66

7) Discovering Multimodal Behavior in Ms. Pac-Man Through Evolution of Modular Neural Networks
Author(s): J. Schrum; R. Miikkulainen
Page(s): 67 - 81

8) Prolog-Scripted Tactics Negotiation and Coordinated Team Actions for Counter-Strike Game Bots
Author(s): G. Jaśkiewicz
Page(s): 82 - 88

9) Predicting Opponent's Production in Real-Time Strategy Games With Answer Set Programming
Author(s): M. Stanescu; M. Čertický

10) How to Run a Successful Game-Based AI Competition
Author(s): J. Togelius
Page(s): 95 - 100

Call for Papers: ICTAI 2016

The 28th International Conference on Tools with Artificial Intelligence, November 07-09, 2016, San Jose, CA

The annual IEEE International Conference on Tools with Artificial Intelligence (ICTAI) provides a major international forum where the creation and exchange of ideas related to artificial intelligence are fostered among academia, industry, and government agencies. The conference facilitates the cross-fertilization of these ideas and promotes their transfer into practical tools, for developing intelligent systems and pursuing artificial intelligence applications. The ICTAI encompasses all technical aspects of specifying, developing and evaluating the theoretical underpinnings and applied mechanisms of the AI-based components of computer tools such as algorithms, architectures and languages.

Topics (not limited to)

AI Foundations

• Evolutionary computing, Bayesian and Neural Networks
• Decision/Utility Theory and Decision Optimization
• Search, SAT, and CSP
• Description Logic and Ontologies

AI in Domain Specific Application

• AI in Natural Language Processing and Understanding
• AI in Computational Biology, Medicine and Biomedical Applications
• AI in WWW, Communication, Social Networking, Recommender Systems, Games and  

E-Commerce

• AI in Finance and Risk Management

AI in Computer Systems

• AI in Robotics, Computer Vision and Games
• AI in Software Engineering, Real-Time and Embedded Applications, and Sensor Networks
• AI in Cloud Computing, Data-Intensive Applications and Online/Streaming and Multimedia Systems
• AI in Web search and Information Retrieval
• AI in Computer Security, Data Privacy, and Information Assurance

AI in Data Analytics and Big Data

• Visualization Analytics for Big Data 
   
• Computational Modeling for Big Data
    
• Large-scale Recommendation and Social Media Systems
• Cloud/Grid/Stream Data Mining for Big Velocity Data 
       
• Semantic-based Big Data Mining

Machine Learning and Data Mining

• Data pre-processing, reduction and feature selection
• Learning Graphical Models and Complex Networks
• Active, Cost-Sensitive, Semi-Supervised, Multi-Instance, Multi-Label and Multi-Task Learning
• Transfer/Adaptive, Rational and Structured Learning
• Preference/Ranking, Ensemble, and Reinforcement Learning

Knowledge Representation, Reasoning and Cognitive Modelling

• Knowledge Representation, Reasoning
• Knowledge Extraction, Management and Sharing
• Case-Based Reasoning and Knowledge-based Systems
• Cognitive Modelling and Semantic Web

AI and Decision Systems

• Decision Guidance and Support Systems
• Optimization-based recommender systems 
• Group, distributed, and collaborative decisions
• Crowd-sourcing and collective intelligence decision making
• Strategic, tactical and operational level decisions 
• Decision making in social and mobile networks

Uncertainty in AI

• Uncertainty and Fuzziness Representation and Reasoning
• Approximate/Exact Probabilistic Inference
• Knowledge Discovery and Data Mining for Uncertain Data

Paper submission: June 30, 2016
Paper notification: July 30, 2016
Camera ready paper: August 30, 2016

Paper Submission
The submissions should contain original, high quality, not submitted or published elsewhere work. Papers should be submitted electronically (through ICTAI 2016 web site) in pdf format and should conform to IEEE specifications (single-spaced, double-column, 10-point font size, up to 8 pages).

Paper Presentation
Each accepted paper should be presented by one of the authors and accompanied by at least one full registration fee payment, to guarantee publication in the proceedings. All accepted papers will be included in proceedings of ICTAI 2016 that will be published by the IEEE Computer Society.

IJAIT special issue and Best Student Papers Awards
Extended versions of the best papers of the conference will be invited for publication in a special issue of the International Journal on Artificial Intelligence Tools (IJAIT) (SCI Indexed). We also provide financial awards to the top-5 best student papers.

Further Information email Chairs:

General Chair: iiass.annaesp@tin.it

Program Chairs:
mali@uwm.edu
malamani@purdue.edu

ICTAI Steering Committee
Nikolaos Bourbakis, Wright State Univ., USA (Chair)
BAIF Steering Committee
Despina Kavraki, BAIF, USA (Chair)

General Chairs
Anna Esposito, Seconda Università di Napoli, Caserta, Italy

Program Co-Chairs
Amol Mali, Univ. of Wisconsin, USA
Miltos Alamaniotis, Purdue Univ, USA

Financial ChairN. Bourbakis, CART-WSU USA

Local Arrangement Chair
R. Kannavara, Intel, OR

Registration Chairs
EASYCHAIR

Publicity Chair and Web Master
A. Angeleas, Z. Chasparis, CART-WSU

ICTAI Program Areas Chairs
A. Awekar, India
V. Balas, Romania
A. Cesta, Italy
D. Dou, USA
J. Gao, USA
M. Ghalwash, USA
E.  Grégoire, France
X. Hu, USA
C. Lim, Australia
M-W. Mak, Hong Kong
Z. Malik, USA
H. Narayanan, USA
A. Orlandini, Italy
K. Palaniappan, USA
N. Rowe, USA
A. Salah, Turkey
B. Schuller, Germany
X. Song, USA
C.Vogel, Ireland
R. Wallace, Ireland
R. Wei, Singapore
C. Yuan, USA
Z-H. Zhou, China

Weekly Review 11 March 2016

Some interesting links that I Tweeted about in the last week:

1. Automated data mining: http://www.kdnuggets.com/2016/03/automated-data-science.html
2. Tracking sources of food poisoning using machine learning of tweets about restaurants: http://www.nsf.gov/news/news_summ.jsp?cntn_id=137848&org=NSF&from=news
3. How NoSQL changed machine learning: http://www.datasciencecentral.com/profiles/blogs/how-nosql-fundamentally-changed-machine-learning
4. Using deep learning to identify bodies of water in orbital images: https://www.technologyreview.com/s/600866/how-deep-learning-gives-us-a-precise-picture-of-all-the-water-on-earth/
5. Why researchers are using Sci-Hub: https://www.insidehighered.com/blogs/library-babel-fish/fix-isnt
6. DeepMind's Alphago is set to take on the world's best Go player: http://www.theguardian.com/technology/2016/mar/07/go-board-game-google-alphago-lee-se-dol
7. I know what it's like to be the first (and so far only) one in the family to go to university: https://www.insidehighered.com/advice/2013/03/04/essay-impact-being-first-generation-college-grad-when-one-joins-academic
8. Is London becoming a centre for AI businesses? http://www.theguardian.com/technology/2016/mar/05/artificial-intelligence-brains-money-london
9. Number of people doing post-docs seems to be declining: http://www.sciencemag.org/careers/2015/12/case-disappearing-postdocs - I'm not surprised: http://computational-intelligence.blogspot.co.nz/2012/09/on-being-post-doc.html 
10. Calls for a royal commission to investigate the impact of robotics on UK jobs: http://www.theguardian.com/technology/2016/mar/08/government-urged-investigate-impact-robots-uk-workforce 
11. Post-grad students should be teaching under-grads: https://www.insidehighered.com/news/2016/03/08/study-suggests-graduate-student-instructors-influence-undergraduates-major 
12. Human vs machine Go tournament has started: http://motherboard.vice.com/en_au/read/tonight-watch-a-professional-go-player-take-on-googles
13. Why you should learn both R and Python: http://www.kdnuggets.com/2016/03/r-python-learning-both-datacamp.html 
14. 29% of software developers are afraid AI will replace them: http://www.computerworld.com/article/3041430/it-careers/one-in-three-developers-fear-ai-will-replace-them.html 
15. AlphaGo won the first match against the world Go champion: http://spectrum.ieee.org/tech-talk/robotics/artificial-intelligence/alphago-wins-game-one-against-world-go-champion
16. Microsoft is including R in Visual Studio now http://www.theregister.co.uk/2016/03/10/open_source_stats_visual_studio/
17. List of tutorials on Scikit-Learn http://www.datasciencecentral.com/profiles/blogs/scikit-learn-tutorial-series 
18. Avoiding the "technical debt" of machine learning: http://www.datanami.com/2016/03/09/how-to-avoid-the-technical-debt-of-machine-learning/
19. AlphaGo has now won two matches in a row against world Go champion: http://phys.org/news/2016-03-human-champion-speechless-2nd-loss.html
20. "Computer conservationists": http://community.lovenature.com/2016/03/10/explore-the-incredible-work-of-computer-conservationists/ I think "Computational conservationist" is a better term, they don't conserve computers

Neural Networks, Volume 76 , Pages 1-152, April 2016

1. Pinning cluster synchronization in an array of coupled neural networks under event-based mechanism  
Author(s): Lulu Li, Daniel W.C. Ho, Jinde Cao, Jianquan Lu
Pages: 1-12

2. Effects of self-coupling and asymmetric output on metastable dynamical transient firing patterns in arrays of neurons with bidirectional inhibitory coupling  
Author(s): Yo Horikawa
Pages: 13-28

3. A Fast Reduced Kernel Extreme Learning Machine  
Author(s): Wan-Yu Deng, Yew-Soon Ong, Qing-Hua Zheng
Pages: 29-38

4. A local Echo State Property through the largest Lyapunov exponent  
Author(s): Gilles Wainrib, Mathieu N. Galtier
Pages: 39-45

5. Finite-time robust stabilization of uncertain delayed neural networks with discontinuous activations via delayed feedback control  
Author(s): Leimin Wang, Yi Shen, Yin Sheng
Pages: 46-54

6. Quantum perceptron over a field and neural network architecture selection in a quantum computer  
Author(s): Adenilton José da Silva, Teresa Bernarda Ludermir, Wilson Rosa de Oliveira
Pages: 55-64

7. Learning contextualized semantics from co-occurring terms via a Siamese architecture  
Author(s) Ubai Sandouk, Ke Chen
Pages 65-96

8. Projective synchronization of nonidentical fractional-order neural networks based on sliding mode controller  
Author(s): Zhixia Ding, Yi Shen
Pages: 97-105

9. An ensemble of dynamic neural network identifiers for fault detection and isolation of gas turbine engines  
Author(s): M. Amozegar, K. Khorasani
Pages: 106-121

10. Hybrid feedback feedforward: An efficient design of adaptive neural network control  
Author(s): Yongping Pan, Yiqi Liu, Bin Xu, Haoyong Yu
Pages: 122-134

11. Multi-source adaptation joint kernel sparse representation for visual classification  
Pages 135-151
Author(s) JianWen Tao, Wenjun Hu, Shiting Wen

Weekly Review 4 March 2016

Some interesting links that I Tweeted about in the last week:

1. A short history of machine learning: http://www.datasciencecentral.com/profiles/blogs/a-short-history-of-machine-learning
2. Machines predicting human behaviour by reading (a lot of) fiction: https://thestack.com/cloud/2016/02/26/computers-read-1-8-billion-words-of-fiction-to-learn-how-to-anticipate-human-behaviour/
3. Helping the disabled with artificial intelligence: http://www.kdnuggets.com/2016/03/data-science-disability.html 
4. Chips made of biological neurons: http://motherboard.vice.com/en_au/read/komiku-neuron-computer-agabi
5. I am so glad that I left Australia four years ago - I couldn't publish my research under these rules https://theconversation.com/new-defence-trade-controls-threaten-academic-freedom-and-the-economy-55310
6. AI won't save us from the bad guys in computer security http://www.theregister.co.uk/2016/03/01/security_ai_rsa_boss/ 
7. TensorFlow now does distributed computing http://www.kdnuggets.com/2016/03/distributed-tensorflow-arrived.html 
8. The key to good teamwork is being nice, according to a many-year study by Google: http://qz.com/625870/after-years-of-intensive-analysis-google-discovers-the-key-to-good-teamwork-is-being-nice/ 
9. How to get into a career in machine learning: http://www.datasciencecentral.com/profiles/blogs/repost-xavier-amatriain-how-should-one-start-a-career-in-machine- 
10. Principal component analysis in R: http://www.bigdatanews.com/profiles/blogs/principal-component-analysis-using-r 
11. Feature selection in Python using scikit-feature http://www.kdnuggets.com/2016/03/scikit-feature-open-source-feature-selection-python.html 
12. Hacking systems with AI: http://www.theguardian.com/technology/2016/mar/03/artificial-intelligence-hackers-security-autonomous-learning
13. How do you control a super-smart AI? http://www.theregister.co.uk/2016/03/04/controlling_smart_ai_systems/
14. Lecture on different deep-learning packages: http://cs231n.stanford.edu/slides/winter1516_lecture12.pdf

IEEE Transactions on Neural Networks and Learning Systems, Volume 27, Issue 3, March 2016.

1. Neural Network-Based Event-Triggered State Feedback Control of Nonlinear Continuous-Time Systems
Authors: Avimanyu Sahoo; Hao Xu; Sarangapani Jagannathan
Page(s): 497 - 509

2. Robust Adaptive Neural Tracking Control for a Class of Stochastic Nonlinear Interconnected Systems
Authors: Huanqing Wang; Xiaoping Liu; Kefu Liu
Page(s): 510 - 523

3. Generating Highly Accurate Predictions for Missing QoS Data via Aggregating Nonnegative Latent Factor Models
Authors: Xin Luo; MengChu Zhou; Yunni Xia; Qingsheng Zhu; Ahmed Chiheb Ammari; Ahmed Alabdulwahab
Page(s): 524 - 537

4. Comparison of Seven Methods for Boolean Factor Analysis and Their Evaluation by Information Gain
Authors: Alexander A. Frolov; Dusan Husek; Pavel Yu. Polyakov
Page(s): 538 - 550

5. A New Stochastic Computing Methodology for Efficient Neural Network Implementation
Authors: DVincent Canals; Antoni Morro; Antoni Oliver; Miquel L. Alomar; Josep L. Rossello
Page(s): 551 - 564

6. Hierarchical Theme and Topic Modeling
Authors: Jen-Tzung Chien
Page(s): 565 - 578

7. A Nonnegative Latent Factor Model for Large-Scale Sparse Matrices in Recommender Systems via Alternating Direction Method
Authors: Xin Luo; MengChu Zhou; Shuai Li; Zhuhong You; Yunni Xia; Qingsheng Zhu
Page(s): 579 - 592

8. Global Exponential Stability for Complex-Valued Recurrent Neural Networks With Asynchronous Time Delays
Authors: Xiwei Liu; Tianping Chen
Page(s): 593 - 606

9. Perception Evolution Network Based on Cognition Deepening Model—Adapting to the Emergence of New Sensory Receptor
Authors: Youlu Xing; Furao Shen; Jinxi Zhao
Page(s): 607 - 620

10. A Spiking Neural Network System for Robust Sequence Recognition
Authors: Qiang Yu; Rui Yan; Huajin Tang; Kay Chen Tan; Haizhou Li
Page(s): 621 - 635

11. DC Proximal Newton for Nonconvex Optimization Problems
Authors: Alain Rakotomamonjy; Remi Flamary; Gilles Gasso
Page(s): 636 - 647

12. Relevance Vector Machine for Survival Analysis
Authors: Farkhondeh Kiaee; Hamid Sheikhzadeh; Samaneh Eftekhari Mahabadi
Page(s): 648 - 660

13. Analog Programmable Distance Calculation Circuit for Winner Takes All Neural Network Realized in the CMOS Technology
Authors: Tomasz Talaska; Marta Kolasa; Rafal Dlugosz; Witold Pedrycz
Page(s): 661 - 673

14. Image Categorization by Learning a Propagated Graphlet Path
Authors: Luming Zhang; Richang Hong; Yue Gao; Rongrong Ji; Qionghai Dai; Xuelong Li
Page(s): 674 - 685

15. Lag Synchronization of Memristor-Based Coupled Neural Networks via \omega-Measure
Authors: Ning Li; Jinde Cao
Page(s): 686 - 697

16. L_{1}-Minimization Algorithms for Sparse Signal Reconstruction Based on a Projection Neural Network
Authors: Qingshan Liu; Jun Wang
Page(s): 698 - 707

Weekly Review 26 February 2016

Some interesting links that I Tweeted about in the last week:

1. Cloud-based machine learning API: http://www.datasciencecentral.com/profiles/blogs/cloud-machine-learning-apis
2. Deep learning for everyone: http://www.kdnuggets.com/2016/02/opening-deep-learning-everyone.html
3. Feature selection for random forests: http://www.datasciencecentral.com/profiles/blogs/choosing-features-for-random-forests-algorithm
4. Some model evaluation metrics: http://www.analyticsvidhya.com/blog/2016/02/7-important-model-evaluation-error-metrics/?utm_source=feedburner&utm_medium=email&utm_campaign=Feed:%20AnalyticsVidhya%20%28Analytics%20Vidhya%29
5. Being an academic isn't that bad: http://www.theguardian.com/higher-education-network/2016/jan/08/cheer-up-my-academic-colleagues-were-so-lucky-to-do-this-job
6. Why do academics drink so much? http://www.theguardian.com/higher-education-network/2016/jan/22/why-do-academics-drink-so-much Maybe it cuts down the mental cross-talk intelligent people are prone to?
7. Photo geolocation with convolutional neural networks: http://arxiv.org/abs/1602.05314
8. Several libraries for generating music with machine learning: http://www.datasciencecentral.com/profiles/blogs/using-machine-learning-to-generate-music 
9. Deep learning to recognise spoken Mandarin http://www.kdnuggets.com/2016/02/getting-deep-speech-work-mandarin-baidu.html 
10. Similarities between deep learning and Markov chains http://www.datasciencecentral.com/profiles/blogs/is-deep-learning-a-markov-chain-in-disguise 
11. Applying Deepmind AI to emergency room diagnosis https://thestack.com/world/2016/02/25/google-deepmind-applies-ai-to-healthcare-with-nhs-partnership/ 
12. An app using AI to identify dog breeds http://www.kdnuggets.com/2016/02/what-dog-breed-ai-fetch.html 
13. Top 5 skills to become a machine learning expert http://www.analyticbridge.com/profiles/blogs/what-is-machine-learning-top-5-skills-required-to-become-a

Evolving Systems, Volume 7, Number 1

1. Evolving Takagi–Sugeno model based on online Gustafson-Kessel algorithm and kernel recursive least square method
Author(s): Soroosh Shafieezadeh-Abadeh & Ahmad Kalhor
Pages: 1-14

2. Online feature extraction based on accelerated kernel principal component analysis for data stream
Author(s): Annie Anak Joseph, Takaomi Tokumoto & Seiichi Ozawa
Pages: 15-27

3. Real-time vessel behavior prediction
Author(s): Dimitrios Zissis, Elias K. Xidias & Dimitrios Lekkas
Pages: 29-40

4. An extended version of opportunity cost algorithm for communication decisions
Author(s): Hiba Abdelmoumène & Habiba Belleili
Pages: 41-60

5. Potential of evolving AR and ARX models in signal recovering
Author(s): Ahmad Kalhor
Pages: 61-72

Neural Networks Volume 75, Pages 1-196, March 2016

1. A graph-based N-body approximation with application to stochastic neighbor embedding  
Author(s): Eli Parviainen
Pages: 1-11

2. A divide-and-combine method for large scale nonparallel support vector machines  
Author(s): Yingjie Tian, Xuchan Ju, Yong Shi
Pages: 12-21

3. Centralized and decentralized global outer-synchronization of asymmetric recurrent time-varying neural network by data-sampling  
Pages: 22-31
Author(s): Wenlian Lu, Ren Zheng, Tianping Chen

4. Synchronized bifurcation and stability in a ring of diffusively coupled neurons with time delay  
Pages: 32-46
Author(s): Ling Wang, Hongyong Zhao, Jinde Cao

5. Matrix measure based dissipativity analysis for inertial delayed uncertain neural networks  
Pages: 47-55
Author(s): Zhengwen Tu, Jinde Cao, Tasawar Hayat

6. Improved system identification using artificial neural networks and analysis of individual differences in responses of an identified neuron  
Pages: 56-65
Author(s): Alicia Costalago Meruelo, David M. Simpson, Sandor M. Veres, Philip L. Newland

7. Subspace segmentation by dense block and sparse representation  
Pages: 66-76
Author(s): Kewei Tang, David B. Dunson, Zhixun Su, Risheng Liu, Jie Zhang, Jiangxin Dong

8. Neuroplasticity in dynamic neural networks comprised of neurons attached to adaptive base plate  
Pages: 77-83
Author(s): Abdolreza Joghataie, Mehrdad Shafiei Dizaji

9. Finite-time stabilization control for discontinuous time-delayed networks: New switching design  
Pages: 84-96
Author(s): Ling-Ling Zhang, Li-Hong Huang, Zuo-Wei Cai

10. Existence and global exponential stability of periodic solution of memristor-based BAM neural networks with time-varying delays  
Pages: 97-109
Author(s): Hongfei Li, Haijun Jiang, Cheng Hu

11. Multi-view L2-SVM and its multi-view core vector machine  
Pages: 110-125
Author(s): Chengquan Huang, Fu-lai Chung, Shitong Wang

12. Cross-validation of matching correlation analysis by resampling matching weights  
Pages: 126-140
Author(s): Hidetoshi Shimodaira

13. Neuro-genetic system for optimization of GMI samples sensitivity  
Pages: 141-149
Author(s): A.C.O. Pitta Botelho, M.M.B.R. Vellasco, C.R. Hall Barbosa, E. Costa Silva

14. Two fast and accurate heuristic RBF learning rules for data classification  
Author(s): Modjtaba Rouhani, Dawood S. Javan
Pages: 150-161

15. Exponential stabilization and synchronization for fuzzy model of memristive neural networks by periodically intermittent control  
Author(s): Shiju Yang, Chuandong Li, Tingwen Huang
Pages: 162-172

16. A theory of cerebellar cortex and adaptive motor control based on two types of universal function approximation capability  
Author(s): Masahiko Fujita
Pages: 173-196

Weekly Review 19 February 2016

Some interesting links that I Tweeted about in the last week:

1. "Illegally" sharing research articles-and of course it's Elsevier suing over it: http://www.sciencealert.com/this-woman-has-illegally-uploaded-millions-of-journal-articles-in-an-attempt-to-open-up-science
2. Seriously, Elsevier, just stop being such ridiculously greedy dicks! http://www.sciencealert.com/this-woman-has-illegally-uploaded-millions-of-journal-articles-in-an-attempt-to-open-up-science
3. Ensembles in machine learning: http://www.kdnuggets.com/2016/02/ensemble-methods-techniques-produce-improved-machine-learning.html I used ensembles of MLP years ago to model an ecoinformatics problem.
4. Elsevier is the Walter White of journal publishers: http://bigthink.com/neurobonkers/a-pirate-bay-for-science
5. High-impact journals are more likely to have fraudulent research published in them: http://journal.frontiersin.org/article/10.3389/fnhum.2013.00291/full
6. AI could drive global unemployment to 50 % http://www.theguardian.com/technology/2016/feb/13/artificial-intelligence-ai-unemployment-jobs-moshe-vardi
7. NSA uses ML to detect terrorists in Pakistan, but doesn't use an independent validation data set to test performance http://arstechnica.co.uk/security/2016/02/the-nsas-skynet-program-may-be-killing-thousands-of-innocent-people/ 
8. For smart people, the NSA seem to have made a pretty basic error with their machine learning http://arstechnica.co.uk/security/2016/02/the-nsas-skynet-program-may-be-killing-thousands-of-innocent-people/
9. Bayes' Theorem for computer scientists http://www.kdnuggets.com/2016/02/bayes-theorem-computer-scientists-explained.html
10. Naive Bayesian classifier explained http://www.datasciencecentral.com/profiles/blogs/the-naive-bayes-classifier-explained
11. Jobs that are threatened by AI: http://www.datasciencecentral.com/profiles/blogs/which-jobs-will-ai-artificial-intelligence-kill
12. Artificial intelligence X-prize: http://www.theverge.com/2016/2/17/11032004/x-prize-ai-contest-ibm-watson-ted-2020 
13. AWS machine learning service only offers one algorithm: http://www.kdnuggets.com/2016/02/amazon-machine-learning-nice-easy-simple.html
14. Add-on allows for fuzzy matching in Google spreadsheets http://www.datasciencecentral.com/profiles/blogs/google-spreadsheet-add-ons-for-data-analysis
15. Marvin Minsky's legacy http://spectrum.ieee.org/computing/software/marvin-minskys-legacy-of-students-and-ideas
16. 40 ways researchers achieved impact with their research http://www.fasttrackimpact.com/#!40-practical-tips-for-achieving-impact-told-to-us-by-researchers-and-those-they-worked-with-to-achieve-impact/hmlp3/569faeba0cf2bfd5cce91b1b