Computational Intelligence

I was travelling on business, and got behind on the weekly review posts. Here is a review of the links that I tweeted about over the last three weeks:

Facebook's race to catch-up in AI: http://www.fastcompany.com/3060570/facebooks-formula-for-winning-at-ai
How AI is making inroads into the legal profession: http://www.thecollegefix.com/post/27773/
Google vs Baidu in speech recognition: http://techcrunch.com/2016/06/11/google-baidu-and-the-race-for-an-edge-in-the-global-speech-recognition-market/
A philosopher's views on the dangers of artificial intelligence: https://www.theguardian.com/technology/2016/jun/12/nick-bostrom-artificial-intelligence-machine
Five ways engineers can improve their writing: http://theinstitute.ieee.org/career-and-education/career-guidance/five-ways-engineers-can-improve-their-writing
Dango uses neural networks to recommend emojis: http://motherboard.vice.com/en_au/read/with-dango-app-ai-is-learning-to-meme
Watch Sunspring, a sci-fi movie written by an AI: http://techcrunch.com/2016/06/11/watch-this-short-sci-fi-movie-with-a-script-written-by-an-ai/
Using machine learning to fight ransomeware: http://www.datanami.com/2016/06/14/machine-learning-enlisted-fight-ransomware/
How to select the kernel of a support vector machine: http://www.kdnuggets.com/2016/06/select-support-vector-machine-kernels.html
Next step for AI research is how they can learn on their own: http://theinstitute.ieee.org/technology-focus/technology-topic/the-next-step-for-artificial-intelligence-is-machines-that-get-smarter-on-their-own
Where machine learning is going to disrupt businesses next: http://tomtunguz.com/key-ingredient-machine-learning/?platform=hootsuite
AI have now passed the Turing test for sound: http://www.techrepublic.com/article/how-new-ai-fools-humans-into-thinking-artificial-sounds-are-real/
Springboard, Google's enterprise AI assistant: http://techcrunch.com/2016/06/14/google-launches-springboard-an-ai-powered-assistant-for-its-enterprise-customers/
Apple is opening-up Siri to third-party developers: http://www.computerworld.com/article/3083149/mac-os-x/apple-touts-a-i-in-ios-and-opens-crown-jewels-to-devs.html - Joining other companies with open AI platforms
How to construct parsimonious binary classification trees: http://www.kdnuggets.com/2016/06/breiman-stone-parsimonious-binary-classification-trees.html
I think every academic has come across a workplace bully at some time, academia attracts egotistical people: https://www.insidehighered.com/advice/2016/06/15/advice-dealing-bullying-behavior-essay
A neural network-based system that turns rough sketches into photorealistic portraits: https://www.technologyreview.com/s/601684/machine-vision-algorithm-learns-to-transform-hand-drawn-sketches-into-photorealistic-images/ Includes link to paper
Finding bugs with AI: http://motherboard.vice.com/en_au/read/cyber-grand-challenge The ultimate goal is to patch the bugs, too.
Is the future of smartphones a single AI? http://www.theverge.com/2016/6/14/11939310/andy-rubin-google-android-playground-ai-robotics
Developing an "ethical" AI that can make life-or-death decisions: http://www.techrepublic.com/article/building-ethical-machines-how-it-can-help-ai-make-life-or-death-decisions/
How is AI going to surprise us in the future? http://www.kdnuggets.com/2016/06/how-much-ai-surprise.html
Six lessons for getting the best out of machine learning: http://www.techrepublic.com/article/ibm-watson-six-lessons-from-an-early-adopter-on-how-to-do-machine-learning/
Using deep learning neural networks for drug discovery: http://scienmag.com/deep-learning-system-for-drug-discovery-to-be-presented-at-the-machine-intelligence-summit-in-berlin/
A smart car dashcam that rates everyone else's driving: http://spectrum.ieee.org/cars-that-think/transportation/sensors/the-ai-dashcam-app-that-wants-to-rate-every-driver-in-the-world?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+IeeeSpectrum+%28IEEE+Spectrum%29&utm_content=FaceBook
A concise history of data mining: http://dataconomy.com/history-data-mining/
How to get started with mining Twitter data with Python: http://www.kdnuggets.com/2016/06/mining-twitter-data-python-part-1.html
A nice overview of the key concepts of machine learning for people who know nothing about it: http://www.techrepublic.com/article/machine-learning-the-smart-persons-guide/
Using machine learning to buy advertising: http://www.datasciencecentral.com/profiles/blogs/when-milliseconds-count-using-ai-to-buy-advertising
Neural networks and the future of AI: https://techcrunch.com/2016/06/16/neural-networks-artificial-intelligence-and-our-future/
Using machine learning to improve performance of power plants: http://www.informationweek.com/iot/ge-uses-machine-learning-to-restore-italian-power-plant/d/d-id/1325918?
A basic explanation of how backpropagation works: http://www.kdnuggets.com/2016/06/visual-explanation-backpropagation-algorithm-neural-networks.html
Google has opened a dedicated machine learning research lab in Zurich: http://www.informationweek.com/big-data/big-data-analytics/google-launches-ai-machine-learning-research-center-/d/d-id/1325942
On the importance of open API for data science: http://www.kdnuggets.com/2016/06/open-api-economy-growth-big-data-analytics.html
Analysing sport teams play using machine learning - heading towards an AI coach? http://motherboard.vice.com/en_au/read/coach-bots-nba-ai
Student evaluations of lecturers are very blunt instruments, it's not surprising that there is bias in them: https://www.insidehighered.com/advice/2016/06/17/removing-bias-student-evaluations-faculty-members-essay
Machine learning for personalised advertising: http://www.pubexec.com/article/the-future-of-marketing-will-be-built-on-personalization-artificial-intelligence/
Machine learning libraries in Javascript: http://www.kdnuggets.com/2016/06/top-machine-learning-libraries-javascript.html
We're getting close to Sci-Fi levels of AI: http://www.huffingtonpost.com/entry/the-amazing-artificial-intelligence-we-were-promised-is-coming-finally_b_10592674.html?section=india
Future trends in AI: http://www.kdnuggets.com/2016/06/machine-learning-trends-future-ai.html
Machine learning with Python for complete beginners: http://pythonforengineers.com/machine-learning-for-complete-beginners/
A brief, point-by-point history of data mining: http://www.kdnuggets.com/2016/06/rayli-history-data-mining.html
A short FAQ on RankBrain, how Google applies deep learning to search: http://searchengineland.com/faq-all-about-the-new-google-rankbrain-algorithm-234440#.V2xDOlIYrKc.twitter
Review of deep learning models and applications: http://www.kdnuggets.com/2016/06/review-deep-learning-models.html
Generating sculptures with a deep neural network and an EA: http://www.popsci.com/creative-ai-learns-to-sculpt-3d-printable-objects
Five myths about machine learning: http://www.forbes.com/sites/teradata/2015/11/13/five-myths-about-machine-learning-you-need-to-know-today/#37831dd2275c
According to this article, compliance is the knowledge job most likely to be taken over by AI: https://hbr.org/2016/06/the-knowledge-jobs-most-likely-to-be-automated
Identifying NSFW images using machine learning: http://www.kdnuggets.com/2016/06/algorithmia-improving-nudity-detection-nsfw-image-recognition.html
How Google is putting machine learning into everything: https://backchannel.com/how-google-is-remaking-itself-as-a-machine-learning-first-company-ada63defcb70#.n1ai2xwao
A good argument in favour of all research publications being open-access: http://arstechnica.com/science/2016/06/what-is-open-access-free-sharing-of-all-human-knowledge/
The impact of machine-generated screenplays: http://motherboard.vice.com/en_au/read/how-machine-generated-screenplays-may-affect-artists
The AI lawyer named Ross has been hired by its first real law firm: http://futurism.com/artificially-intelligent-lawyer-ross-hired-first-official-law-firm/
An AI that predicts human actions after being trained on TV programmes: http://www.geekwire.com/2016/computer-binge-watches-tv-predict-ai/
Google's suggested rules for AI that prevent AI from becoming harmful: http://www.extremetech.com/extreme/230718-google-researchers-tackle-ai-and-robotics-safety-prevent-future-toasters-from-killing-us-in-our-sleep
A cheat-sheet on machine learning algorithms: http://www.datasciencecentral.com/profiles/blogs/the-making-of-a-cheatsheet-emoji-edition
Applying cloud-based intelligence to off-the-shelf robots: http://www.theverge.com/circuitbreaker/2016/6/24/12027808/tend-ai-cloud-machine-learning-co-working-robots
AI will create jobs as well as destroy jobs - it just won't create as many jobs as it destroys: http://www.informationweek.com/strategic-cio/it-strategy/robots-ai-wont-destroy-jobs-yet/d/d-id/1326056
A beginners experiences with deep learning: https://www.theguardian.com/technology/2016/jun/28/google-says-machine-learning-is-the-future-so-i-tried-it-myself
Predictions that AI will replace 16 % of white collar jobs by 2025, but create another 9 %: http://www.theregister.co.uk/2016/06/28/forrester_reports_ai_will_create_jobs/
An adaptive AI for air combat: http://www.newsmax.com/Newsfront/air-force-ai-top-gun-software/2016/06/27/id/735925/
Google has built an AI that picks out the most important parts of an image: https://techcrunch.com/2016/06/28/google-researchers-teach-ais-to-see-the-important-parts-of-images-and-tell-you-about-them/
According to the paper, the air combat AI is a genetic-fuzzy system: http://www.omicsgroup.org/journals/genetic-fuzzy-based-artificial-intelligence-for-unmanned-combat-aerialvehicle-control-in-simulated-air-combat-missions-2167-0374-1000144.php?aid=72227
An overview of deep learning: http://www.datasciencecentral.com/profiles/blogs/guide-to-deep-learning
Why we need to stop worrying about AI: http://fortune.com/2016/06/28/artificial-intelligence-potential/
A list of deep learning libraries in different languages: http://www.datasciencecentral.com/profiles/blogs/deep-learning-libraries-by-language
Landing a job in artificial intelligence: http://theinstitute.ieee.org/technology-focus/technology-topic/how-to-land-a-job-in-artificial-intelligence
Infographic on the current state of artificial intelligence: http://www.datasciencecentral.com/profiles/blogs/the-state-of-artificial-intelligence-infographic
Looking inside convolutional neural networks: http://www.kdnuggets.com/2016/06/peeking-inside-convolutional-neural-networks.html
Are journal editors cheating the impact factor measure? https://www.insidehighered.com/views/2016/07/01/examination-whether-academic-journal-rankings-are-being-manipulated-essay
Predicting cancer metastasis - seems to be using machine learning of some description: http://www.digitaltrends.com/cool-tech/cancer-spread-prediction-algorithm/
I like #4, "don't multi-task". I have to keep reminding myself "one thing at a time!" https://elearningindustry.com/5-ways-survive-student-email-avalanche
Although to be honest, it's not an avalanche of email from students that usually takes up my time: https://elearningindustry.com/5-ways-survive-student-email-avalanche
Brief introduction to text mining: http://www.kdnuggets.com/2016/07/text-mining-101-topic-modeling.html
Experts' opinions on Satya Nadella's 10 rules for AI: http://www.techrepublic.com/article/ai-experts-weigh-in-on-microsoft-ceos-10-new-rules-for-artificial-intelligence/
The promise, and problems, of machine learning in cybersecurity: https://techcrunch.com/2016/07/01/exploiting-machine-learning-in-cybersecurity/
Intel is tuning its Xeon Phi chips to make them better suited to machine learning: http://www.computerworld.com/article/3090991/computer-hardware/intel-tunes-its-mega-chip-for-machine-learning.html
Satya Nadella calls for accountability in AI, biased systems already exist: https://www.technologyreview.com/s/601812/microsofts-ceo-calls-for-accountable-ai-ignores-the-algorithms-that-already-rule-our-lives/
Implementing recursive neural networks in TensorFlow: http://www.kdnuggets.com/2016/06/recursive-neural-networks-tensorflow.html
AI can see the world, but it doesn't see the world the same way we do: https://www.technologyreview.com/s/601819/ai-is-learning-to-see-the-world-but-not-the-way-humans-do/

Saturday, July 2, 2016

IEEE Transactions on Neural Networks and Learning Systems;Volume 27, Issue 7, July 2016.

1. Probe Machine
Author(s): Jin Xu
Page(s): 1405 - 1416

2. Learning Compositional Shape Models of Multiple Distance Metrics by Information Projection
Author(s): Ping Luo; Liang Lin; Xiaobai Liu
Page(s): 1417 - 1428

3. Comparison Analysis: Granger Causality and New Causality and Their Applications to Motor Imagery
Author(s): Sanqing Hu; Hui Wang; Jianhai Zhang; Wanzeng Kong; Yu Cao; Robert Kozma
Page(s): 1429 - 1444

4. Alternative Multiview Maximum Entropy Discrimination
Author(s): Guoqing Chao; Shiliang Sun
Page(s): 1445 - 1456

5. Parallel Online Temporal Difference Learning for Motor Control
Author(s): Wouter Caarls; Erik Schuitema
Page(s): 1457 - 1468

6. Sparse Uncorrelated Linear Discriminant Analysis for Undersampled Problems
Author(s): Xiaowei Zhang; Delin Chu; Roger C. E. Tan
Page(s): 1469 - 1485

7. Stability Analysis for Delayed Neural Networks Considering Both Conservativeness and Complexity
Author(s): Chuan-Ke Zhang; Yong He; Lin Jiang; Min Wu
Page(s): 1486 - 1501

8. Compound Rank-k Projections for Bilinear Analysis
Author(s): Xiaojun Chang; Feiping Nie; Sen Wang; Yi Yang; Xiaofang Zhou; Chengqi Zhang
Page(s): 1502 - 1513

9. Constrained Clustering With Nonnegative Matrix Factorization
Author(s): Xianchao Zhang; Linlin Zong; Xinyue Liu; Jiebo Luo
Page(s): 1514 - 1526

10. Control of Large-Scale Boolean Networks via Network Aggregation
Author(s): Yin Zhao; Bijoy K. Ghosh; Daizhan Cheng
Page(s): 1527 - 1536

11. Near-Optimal Controller for Nonlinear Continuous-Time Systems With Unknown Dynamics Using Policy Iteration
Author(s): Samrat Dutta; Prem Kumar Patchaikani; Laxmidhar Behera
Page(s): 1537 - 1549

12. Image Super-Resolution via Adaptive \ell _{p} (0< p< 1) Regularization and Sparse Representation
Author(s): Feilong Cao; Miaomiao Cai; Yuanpeng Tan; Jianwei Zhao
Page(s): 1550 - 1561

13. Neural Network Control-Based Adaptive Learning Design for Nonlinear Systems With Full-State Constraints
Author(s): Yan-Jun Liu; Jing Li; Shaocheng Tong; C. L. Philip Chen
Page(s): 1562 - 1571

14. Learning Spike Time Codes Through Morphological Learning With Binary Synapses
Author(s): Subhrajit Roy; Phyo Phyo San; Shaista Hussain; Lee Wang Wei; Arindam Basu
Page(s): 1572 - 1577

15. Saturated Finite Interval Iterative Learning for Tracking of Dynamic Systems With HNN-Structural Output
Author(s): Wenjun Xiong; Daniel W. C. Ho; Xinghuo Yu
Page(s): 1578 - 1584

16. Pinning Control Design for the Stabilization of Boolean Networks
Author(s): Fangfei Li
Page(s): 1585 - 1590

17. Can the Virtual Labels Obtained by Traditional LP Approaches Be Well Encoded in WLR?
Author(s): Qiaolin Ye; Jian Yang; Tongming Yin; Zhao Zhang
Page(s): :1591 - 1598

Sunday, June 12, 2016

Weekly Review 11 June 2016

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

What happens when you run Bladerunner through a deep-learning autoencoder: http://www.vox.com/2016/6/1/11787262/blade-runner-neural-network-encoding
Concise explanation of the difference between regular machine learning and deep learning: http://www.kdnuggets.com/2016/06/difference-between-deep-learning-regular-machine-learning.html
On why AI needs a "big red button": http://www.theverge.com/2016/6/3/11856744/google-deep-mind-big-red-button-interupt-ai
Data mining unstructured data with deep learning: http://www.datanami.com/2016/06/03/unstructured-data-miners-chase-silver-deep-learning/
How AI is changing SEO: http://techcrunch.com/2016/06/04/artificial-intelligence-is-changing-seo-faster-than-you-think/
How AI-based "Driver Assistance Systems" will dominate the markup before autonomous vehicles: http://www.computerworld.com/article/3079044/car-tech/ai-guardian-angel-vehicles-will-dominate-auto-industry-says-toyota-exec.html
This is the era of AI: http://fortune.com/2016/06/03/tech-ceos-artificial-intelligence/
China's obsession with quantity over quality leads to corruption. fraud in science: http://www.economist.com/news/science-and-technology/21699898-fraud-bureaucracy-and-obsession-quantity-over-quality-still-hold-chinese?fsrc=scn/tw/te/pe/ed/schrdingerspanda
Will Artificial Intelligences end up with human rights? http://www.telegraph.co.uk/science/2016/05/29/computers-could-develop-consciousness-and-may-need-human-rights/
The future of AI on smart phones: http://dataconomy.com/forget-siri-machine-learning-ai-coming-smartphone/
The truth about deep learning: http://www.kdnuggets.com/2016/06/truth-deep-learning.html
Why TensorFlow is a game-changer: http://www.datasciencecentral.com/profiles/blogs/tensorflow-why-google-s-artificial-intelligence-engine-is-a
List of resources for an open-source machine learning degree: http://www.kdnuggets.com/2016/06/open-source-machine-learning-degree.html
How to do machine learning, from Uber's head of machine learning: http://techemergence.com/ubers-head-of-machine-learning-thinks-you-might-be-doing-it-wrong/
Ten frightening uses of AI: http://www.techrepublic.com/pictures/10-terrifying-uses-of-artificial-intelligence/
A new neural processor: http://www.computerworld.com/article/3079349/artificial-intelligence/a-former-nasa-chief-just-launched-this-ai-startup-to-turbocharge-neural-computing.html
A test shows that a medical AI is as accurate on triage as an experienced doctor: http://motherboard.vice.com/en_au/read/a-health-apps-ai-took-on-human-doctors-to-triage-patients
An AI web designer: http://www.techrepublic.com/article/new-wix-adi-uses-artificial-intelligence-to-design-your-small-business-website/
The industries being redefined by machine learning: http://www.forbes.com/sites/louiscolumbus/2016/06/04/machine-learning-is-redefining-the-enterprise-in-2016/#5fd98f705fc0
LinkedIn's contribution to machine learning: http://www.datanami.com/2016/06/07/linkedin-adds-growing-list-ml-tools/
Using AI in human longevity research: http://nextbigfuture.com/2016/06/artificial-intelligence-to-spearhead.html
Combining AI with the power of crowds: http://techcrunch.com/2016/06/07/crowdflower-series-d/
Business opportunities of machine learning: http://www.kdnuggets.com/2016/06/opportunites-machine-learning-startups.html
A new company using AI in computer security: http://www.datanami.com/2016/06/08/another-ai-based-security-startup-gains-funding/
More details about Armorway, startup using AI in computer security: http://www.techrepublic.com/article/armorway-grabs-2-5-million-to-expand-ai-security-platform/
DeepMind's five-year plan for AI in healthcare: http://techcrunch.com/2016/06/08/nhs-memo-details-googledeepminds-five-year-plan-to-bring-ai-to-healthcare/
TensorFlow is now available for iOS: http://www.theverge.com/2016/6/8/11885924/google-tensorflow-release-ios-magenta-neural-network
Artificial intelligence vs cancer: http://www.bbc.com/news/health-36482333
Another company, Cyclance, also using AI for computer security: http://www.computerworld.com/article/3081326/security/this-company-uses-ai-to-stop-cyberattacks-before-they-start.html
Behavioural psychologists are now testing artificial intelligences: https://www.technologyreview.com/s/601646/the-ai-machines-undergoing-behavioral-psychology-tests/
More on Google's Project Magenta, their AI composer: https://www.technologyreview.com/s/601642/ok-computer-write-me-a-song/
A deep neural network rendered 2001: A Space Odyssey in the style of Picasso: http://motherboard.vice.com/en_au/read/a-neural-network-rendered-kubricks-2001-in-the-style-of-pablo-picasso
A free e-book on data science: http://www.datasciencecentral.com/profiles/blogs/free-e-book-exploring-data-science
Google is developing its own version of Asimov's laws of robotics: http://www.extremetech.com/extreme/229806-google-is-starting-to-design-its-own-version-of-asimovs-laws-of-robotics
A whitepaper on AI and machine learning in the insurance industry: http://1.fc-bi.com/LP=12421
A movie written in collaboration with an AI: http://arstechnica.com/the-multiverse/2016/06/an-ai-wrote-this-movie-and-its-strangely-moving/
The security risks of AI: http://www.datanami.com/2016/06/10/ai-coming-prompting-new-security-concerns/
There is still bias in peer review and in funding decisions: http://arstechnica.com/science/2016/06/implicit-bias-still-hinders-minority-researchers/
Google DeepMind is mastering more difficult video games, thanks to curiosity: http://www.theverge.com/2016/6/9/11893002/google-ai-deepmind-atari-montezumas-revenge
With quantum computers will come quantum machine learning: http://nextbigfuture.com/2016/06/google-hartmut-neven-predicts-that.html
The jobs that AI will destroy first: http://www.idgconnect.com/abstract/17250/no-robots-required-ai-eliminate-jobs
Why more women don't code - or even get into IT in general: https://theconversation.com/the-real-reason-more-women-dont-code-59663

Sunday, June 5, 2016

IEEE Transactions on Neural Networks and Learning Systems, Volume 27, Issue 6, June 2016

1) Guest Editorial Special Section on Visual Saliency Computing and Learning
Author(s): Junwei Han; Ling Shao; Nuno Vasconcelos; Jungong Han; Dong Xu
Page(s): 1118 - 1121

2) Manifold Ranking-Based Matrix Factorization for Saliency Detection
Author(s): Dapeng Tao; Jun Cheng; Mingli Song; Xu Lin
Page(s): 1122 - 1134

3) DISC: Deep Image Saliency Computing via Progressive Representation Learning
Author(s): Tianshui Chen; Liang Lin; Lingbo Liu; Xiaonan Luo; Xuelong Li
Page(s): 1135 - 1149

4) Human-Centered Saliency Detection
Author(s): Zhenbao Liu; Xiao Wang; Shuhui Bu
Page(s): 1150 - 1162

5) Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining
Author(s): Dingwen Zhang; Junwei Han; Jungong Han; Ling Shao
Page(s): 1163 - 1176

6) Spatiochromatic Context Modeling for Color Saliency Analysis
Author(s): Jun Zhang; Meng Wang; Shengping Zhang; Xuelong Li; Xindong Wu
Page(s): 1177 - 1189

7) Dual Low-Rank Pursuit: Learning Salient Features for Saliency Detection
Author(s): Congyan Lang; Jiashi Feng; Songhe Feng; Jingdong Wang; Shuicheng Yan
Page(s): 1190 - 1200

8) Improving Visual Saliency Computing With Emotion Intensity
Author(s): Huiying Liu; Min Xu; Jinqiao Wang; Tianrong Rao; Ian Burnett
Page(s): 1201 - 1213

9) Reconciling Saliency and Object Center-Bias Hypotheses in Explaining Free-Viewing Fixations
Author(s): Ali Borji; James Tanner
Page(s): 1214 - 1226

10) Bottom–Up Visual Saliency Estimation With Deep Autoencoder-Based Sparse Reconstruction
Author(s): Chen Xia; Fei Qi; Guangming Shi
Page(s): 1227 - 1240

11) Learning to Predict Sequences of Human Visual Fixations
Author(s): Ming Jiang; Xavier Boix; Gemma Roig; Juan Xu; Luc Van Gool; Qi Zhao
Page(s): 1241 - 1252

12) Saliency-Aware Nonparametric Foreground Annotation Based on Weakly Labeled Data
Author(s): Xiaochun Cao; Changqing Zhang; Huazhu Fu; Xiaojie Guo; Qi Tian
Page(s): 1253 - 1265

13) The Application of Visual Saliency Models in Objective Image Quality Assessment: A Statistical Evaluation
Author(s): Wei Zhang; Ali Borji; Zhou Wang; Patrick Le Callet; Hantao Liu
Page(s): 1266 - 1278

14) Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking
Author(s): Qi Wang; Jianzhe Lin; Yuan Yuan
Page(s): 1279 - 1289

15) Guest Editorial Special Section on Learning in Non-(geo)metric Spaces
Author(s): Marcello Pelillo; Edwin R. Hancock; Xuelong Li; Vittorio Murino
Page(s): 1290 - 1293

16) Sparse Coding on Symmetric Positive Definite Manifolds Using Bregman Divergences
Author(s): Mehrtash T. Harandi; Richard Hartley; Brian Lovell; Conrad Sanderson
Page(s): 1294 - 1306

17) Multicriteria Similarity-Based Anomaly Detection Using Pareto Depth Analysis
Author(s): Ko-Jen Hsiao; Kevin S. Xu; Jeff Calder; Alfred O. Hero
Page(s): 1307 - 1321

18) Learning in Variable-Dimensional Spaces
Author(s): Michelangelo Diligenti; Marco Gori; Claudio Saccà
Page(s): 1322 - 1332

19) Manifold Learning for Multivariate Variable-Length Sequences With an Application to Similarity Search
Author(s): Shen-Shyang Ho; Peng Dai; Frank Rudzicz
Page(s): 1333 - 1344

20) Constrained Clustering With Imperfect Oracles
Author(s): Xiatian Zhu; Chen Change Loy; Shaogang Gong
Page(s): 1345 - 1357

21) Hierarchical Image Segmentation Using Correlation Clustering
Author(s): Amir Alush; Jacob Goldberger
Page(s): 1358 - 1367

22) Feature Combination and the kNN Framework in Object Classification
Author(s): Jian Hou; Huijun Gao; Qi Xia; Naiming Qi
Page(s): 1368 - 1378

23) Dissimilarity-Based Ensembles for Multiple Instance Learning
Author(s): Veronika Cheplygina; David M. J. Tax; Marco Loog
Page(s): 1379 - 1391

24) Ensemble Manifold Rank Preserving for Acceleration-Based Human Activity Recognition
Author(s): Dapeng Tao; Lianwen Jin; Yuan Yuan; Yang Xue
Page(s): 1392 - 1404

Saturday, June 4, 2016

IEEE Transactions on Fuzzy Systems, Volume 24, Issue 3

1) Nonfragile H_{\infty } Fuzzy Filtering With Randomly Occurring Gain Variations and Channel Fadings
Author(s): Sunjie Zhang; Zidong Wang; Derui Ding; Hongli Dong; Fuad E. Alsaadi; Tasawar Hayat
Page(s): 505 - 518

2) Chain and Substitution Rules of Intuitionistic Fuzzy Calculus
Author(s): Qian Lei; Zeshui Xu
Page(s): 519 - 529

3) Extended Fuzzy Logic: Sets and Systems
Author(s): Farnaz Sabahi; Mohammad Reza Akbarzadeh-T
Page(s): 530 - 543

4) Fuzzy-Model-Based Robust H_{\infty } Design of Nonlinear Packetized Networked Control Systems
Author(s): Bin Tang; Shiguo Peng; Yun Zhang
Page(s): 544 - 557

5) Extensions of Atanassov's Intuitionistic Fuzzy Interaction Bonferroni Means and Their Application to Multiple-Attribute Decision Making
Author(s): Yingdong He; Zhen He
Page(s): 558 - 573

6) Evolving Type-2 Fuzzy Classifier
Author(s): Mahardhika Pratama; Jie Lu; Guangquan Zhang
Page(s): 574 - 589

7) Multicriteria Decision Making With Ordinal/Linguistic Intuitionistic Fuzzy Sets For Mobile Apps
Author(s): Ronald R. Yager
Page(s): 590 - 599

8) Improving Linguistic Pairwise Comparison Consistency via Linguistic Discrete Regions
Author(s): Hengshan Zhang; Qinghua Zheng; Ting Liu; Zijiang Yang; Minnan Luo; Yu Qu
Page(s): 600 - 614

9) Law of Large Numbers for Uncertain Random Variables
Author(s): Kai Yao; Jinwu Gao
Page(s): 615 - 621

10) Output Feedback Direct Adaptive Fuzzy Controller Based on Frequency-Domain Methods
Author(s): Krzysztof Wiktorowicz
Page(s): 622 - 634

11) Stability and Stabilization of Takagi–Sugeno Fuzzy Systems via Sampled-Data and State Quantized Controller
Author(s): Yajuan Liu; S. M. Lee
Page(s): 635 - 644

12) Parameterizing the Semantics of Fuzzy Attribute Implications by Systems of Isotone Galois Connections
Author(s): Vilem Vychodil
Page(s): 645 - 660

13) Decentralized Sampled-Data Fuzzy Observer Design for Nonlinear Interconnected Systems
Author(s): Geun Bum Koo; Jin Bae Park; Young Hoon Joo
Page(s): 661 - 674

14) Robust Stability Analysis and Systematic Design of Single-Input Interval Type-2 Fuzzy Logic Controllers
Author(s): Tufan Kumbasar
Page(s): 675 - 694

15) Rough-Set-Theoretic Fuzzy Cues-Based Object Tracking Under Improved Particle Filter Framework
Author(s): Pojala Chiranjeevi; Somnath Sengupta
Page(s): 695 - 707

16) Fuzzy Multiobjective Modeling and Optimization for One-Shot Multiattribute Exchanges With Indivisible Demand
Author(s): Zhong-Zhong Jiang; Zhi-Ping Fan; W. H. Ip; Xiaohong Chen
Page(s): 708 - 723

17) Global Fuzzy Adaptive Hierarchical Path Tracking Control of a Mobile Robot With Experimental Validation
Author(s): Chih-Lyang Hwang; Wei-Li Fang
Page(s): 724 - 740

18) Asymmetric Fuzzy Preference Relations Based on the Generalized Sigmoid Scale and Their Application in Decision Making Involving Risk Appetites
Author(s): Wei Zhou; Zeshui Xu
Page(s): 741 - 756

19) Possibilistic Functional Dependencies and Their Relationship to Possibility Theory
Author(s): Sebastian Link; Henri Prade
Page(s): 757 - 763

Weekly Review 3 June 2016

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

Tips for building a successful AI platform, from Facebook's director of machine learning: http://www.techrepublic.com/article/facebooks-machine-learning-director-shares-tips-for-building-a-successful-ai-platform/
Hooray! From 2020, all EU-funded research must be published as open-access. Will more governments follow? http://techcrunch.com/2016/05/27/eu-mandates-open-access-for-all-publicly-funded-research-by-2020/
Point-and-click bot-building: http://venturebeat.com/2016/05/26/motion-ai-lets-anyone-easily-build-a-bot/
Most Americans don't trust AI: http://www.digitaltrends.com/cool-tech/ai-system-trust/#:YvuruZwzPeTsCA I suspect that would apply to people in most countries.
An early prototype system using machine learning to detect potholes for visually-impaired people: http://spectrum.ieee.org/the-human-os/biomedical/devices/pothole-detection-for-the-visually-impaired?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+IeeeSpectrum+%28IEEE+Spectrum%29&utm_content=FaceBook
Basically, everyone is pirating papers - open access is the way ahead https://theconversation.com/is-it-piracy-how-students-access-academic-resources-55712
Personally, I think AI is a long way from the real thing: http://www.cnet.com/news/artificial-intelligence-getting-as-good-as-the-real-thing/
Communicating technical ideas to non-technical people - I've found the same principles apply in teaching http://www.datasciencecentral.com/profiles/blogs/tips-for-effectively-communicating-complex-ideas-to-non-technical
Designing for an AI-enhanced experience: http://www.tandemseven.com/blog/designing-for-ai-enhanced-experiences/
How IBM's Watson can contribute to education: http://www.techinsider.io/how-watson-ai-can-transform-education-2016-5
When an AI can explain to a fresher how an AI works, I will be worried about my job: http://www.edtechmagazine.com/higher/article/2015/02/artificial-intelligence-and-robotics-slowly-enter-college-classrooms
57% of jobs are at risk of being replaced by AI and robots: http://techcrunch.com/2016/05/29/human-obsolescence-are-we-ready-for-an-artificially-intelligent-future/
Machines are going to take all of our jobs: http://www.neowin.net/news/a-robot-is-about-to-take-over-my-job-then-hes-coming-after-yours
Recurrent neural networks in TensorFlow: http://www.kdnuggets.com/2016/05/intro-recurrent-networks-tensorflow.html
Natural language processing for a movie recommendation system: http://techcrunch.com/2016/05/31/this-facebook-bot-will-pick-your-next-movie-for-you/
How machine learning is transforming parts of every day life: http://www.information-management.com/blogs/big-data-analytics/machine-learning-has-transformed-many-aspects-of-everyday-life-10028943-1.html
Why we should care about how people interact with machine learning systems: http://www.kdnuggets.com/2016/05/interacting-machine-learning.html
Why everyone needs to understand machine learning: https://www.weforum.org/agenda/2016/05/why-you-need-to-understand-machine-learning
The argument that AI will augment, rather than replace, people in the workplace: http://www.techrepublic.com/article/robots-beware-humans-will-still-be-bosses-of-machines-say-davenport-and-kirby-in-new-book/
How Facebook is using AI to flag offensive images: http://techcrunch.com/2016/05/31/terminating-abuse/
Who is going to win the race to monetise AI? http://www.cio.com/article/3076154/internet-of-things/the-race-to-monetize-artificial-intelligence-is-on.html
List of resources for machine learning and data science in R and Python: http://www.datasciencecentral.com/profiles/blogs/hitchhiker-s-guide-to-data-science-machine-learning-r-python
DARPA is seeking a mathematical framework on the limitations of machine learning: http://nextbigfuture.com/2016/05/darpa-seeks-mathematical-framework-to.html
Using a social media bot: http://motherboard.vice.com/en_au/read/i-let-a-robot-take-over-my-social-media-for-48-hours
How SAP is using machine learning to help transition its customers to the cloud: http://www.techrepublic.com/article/sap-invests-in-machine-learning-to-simplify-customer-transition-to-cloud/
It's far to early to start regulating AI: https://www.technologyreview.com/s/601563/what-to-do-when-a-robot-is-the-guilty-party/
First example of music produced by Google's AI: http://techcrunch.com/2016/06/01/google-ai-produces-a-melody-that-rivals-the-casio-keyboard-concerts-of-our-youth/
An article on DeepText, Facebook's text-processing natural language system: http://techcrunch.com/2016/06/01/facebook-deep-text/
Some more details on Facebook's DeepText: https://code.facebook.com/posts/181565595577955/introducing-deeptext-facebook-s-text-understanding-engine/
Artificially intelligent headphones. Seriously. http://techcrunch.com/2016/06/01/first-look-lifebeams-artificially-intelligent-headphones-for-that-her-like-workout/
Which AI company is Elon Musk most scared of? http://www.theverge.com/2016/6/2/11837566/elon-musk-one-ai-company-that-worries-me
How Bill Gates sees AI as the "holy grail": http://mashable.com/2016/06/01/bill-gates-ai-code-conference/#odjE.UnZcOqc
On the democratisation of machine learning: http://www.datasciencecentral.com/profiles/blogs/machine-learning-is-dead-long-live-machine-learning
An overview of logistic regression: http://www.analyticbridge.com/profiles/blogs/making-data-science-accessible-logistic-regression
More about Project Magenta, Google artistic AI: http://www.informationweek.com/big-data/big-data-analytics/googles-magenta-project-can-machines-be-musicians/a/d-id/1325752?
A howto on building a deep learning box: http://www.kdnuggets.com/2016/06/build-deep-learning-box.html
CISCO is planning on using IBM's Watson AI to analyse data from the IoT: http://techcrunch.com/2016/06/02/ibm-cisco-iot/
Google's AI is the best, according to CEO Sundar Pichai: http://www.informationweek.com/iot/googles-sundar-pichai-our-ai-beats-competitors-ai/a/d-id/1325758
The "barbell effect" of machine learning - how the benefits of AI will be driven to extreme ends: http://techcrunch.com/2016/06/02/the-barbell-effect-of-machine-learning/

Saturday, May 28, 2016

IEEE Transactions on Evolutionary Computation, Volume 20, Number 3, June 2016

1) A Modified Ant Colony Optimization Algorithm for Network Coding Resource Minimization
Author(s): Zhaoyuan Wang; Huanlai Xing; Tianrui Li; Yan Yang; Rong Qu; Yi Pan
Page(s): 325 - 342

2) Multifactorial Evolution: Toward Evolutionary Multitasking
Author(s): Abhishek Gupta; Yew-Soon Ong; Liang Feng
Page(s): 343 - 357

3) A Unified Evolutionary Optimization Procedure for Single, Multiple, and Many Objective s
Author(s): Haitham Seada; Kalyanmoy Deb
Page(s): 358 - 369

4) Analysis of Stability, Local Convergence, and Transformation Sensitivity of a Variant of the Particle Swarm Optimization Algorithm
Author(s): Mohammad Reza Bonyadi; Zbigniew Michalewicz
Page(s): 370 - 385

5) Visualization and Performance Metric in Many-Objective Optimization
Author(s): Zhenan He; Gary G. Yen
Page(s): 386 - 402

6) Automatic Component-Wise Design of Multiobjective Evolutionary Algorithms
Author(s): Leonardo C. T. Bezerra; Manuel López-Ibáñez; Thomas Stützle
Page(s): 403 - 417

7) A Sparse Spectral Clustering Framework via Multiobjective Evolutionary Algorithm
Author(s): Juanjuan Luo; Licheng Jiao; Jose A. Lozano
Page(s): 418 - 433

8) The Permutation in a Haystack Problem and the Calculus of Search Landscapes
Author(s): Vincent A. Cicirello
Page(s): 434 - 446

9) Constraint Consensus Mutation-Based Differential Evolution for Constrained Optimization
Author(s): Noha M. Hamza; Daryl L. Essam; Ruhul A. Sarker
Page(s): 447 - 459

10) Computing Nash Equilibria and Evolutionarily Stable States of Evolutionary Games
Author(s): Jiawei Li; Graham Kendall; Robert John
Page(s): 460 - 469

11) The $N$ -Player Trust Game and its Replicator Dynamics
Author(s): Hussein Abbass; Garrison Greenwood; Eleni Petraki
Page(s): 470 - 474

12) Constrained Subproblems in a Decomposition-Based Multiobjective Evolutionary Algorithm
Author(s): Luping Wang; Qingfu Zhang; Aimin Zhou; Maoguo Gong; Licheng Jiao
Page(s): 475 - 480

Weekly Review 27 May 2016

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

AI and the rise of the "useless" class: https://www.theguardian.com/technology/2016/may/20/silicon-assassins-condemn-humans-life-useless-artificial-intelligence
Overview of the applications of IBM's Watson: http://www.extremetech.com/extreme/228877-ibm-watson-amps-up-moogfest-2016-with-ai-infused-programming
Machine learning is the "automation of automation": http://www.kdnuggets.com/2016/05/explain-machine-learning-software-engineer.html
The promise of Google's AI: https://www.theguardian.com/technology/2016/may/20/google-ai-machine-learning-skynet-technology
Google Home means holding conversations with computers - will they use those conversations to make better AI? https://www.technologyreview.com/s/601530/google-thinks-youre-ready-to-converse-with-computers/
A knowledge of measurement theory is really important: http://www.kdnuggets.com/2016/05/dont-just-assume-data-interval-scale.html See also here: http://computational-intelligence.blogspot.co.nz/2015/03/measurement-theory.html
China is really going in the wrong direction now. A real shame, I know lots of good people among China's academia: http://www.theguardian.com/world/2016/may/24/academics-china-crackdown-forces-intellectuals-abroad
Australian robot livestock workers: https://www.newscientist.com/article/2089321-robot-ranchers-monitor-animals-on-giant-australian-farms/?utm_source=NSNS&utm_medium=ILC&utm_campaign=webpush&cmpid=ILC%257CNSNS%257C2016-GLOBAL-webpush-ROBOTRANCHERS
Google is trying to teach an AI to be artistic: http://www.theverge.com/2016/5/23/11743948/google-artificial-intelligence-magenta-art-music-project
The (potential) contribution of AI to medicine: http://www.extremetech.com/extreme/228830-the-next-major-advance-in-medicine-will-be-the-use-of-ai
Some thoughts on language choice for writing a web crawler: http://www.bigdatanews.com/profiles/blogs/which-language-is-better-for-writing-a-web-crawler-php-python-or Last crawler I wrote was in Python.
Natural language processing and AI in Facebook: http://www.techrepublic.com/article/why-facebook-wants-to-use-ai-to-track-your-conversations-online/
Facebook is planning on using neural networks for translation: https://www.technologyreview.com/s/601562/facebook-plans-to-boost-its-translations-using-neural-networks-this-year/ That'll need some really, really big neural networks.
What's good and what's bad about TensorFlow: http://www.kdnuggets.com/2016/05/good-bad-ugly-tensorflow.html
The disappointment of AI personalisation: http://www.techrepublic.com/article/big-datas-big-disappointment-why-ai-personalization-is-pathetic/
More than just bots in the intelligent application ecosystem: http://techcrunch.com/2016/05/24/the-intelligent-app-ecosystem-is-more-than-just-bots/
Machine learning algorithms that learn from fewer examples: https://www.technologyreview.com/s/601551/algorithms-that-learn-with-less-data-could-expand-ais-power/
Biased data will give you biased models: http://theinstitute.ieee.org/ieee-roundup/opinions/ieee-roundup/bias-in-code-is-a-problem-that-cannot-be-ignored- I used to teach this to my third-year AI class, why don't pros know?
Why Facebook's AI can't recognise a mirror selfie: http://motherboard.vice.com/en_au/read/why-artificial-intelligence-cant-detect-mirror-selfies
Terrapattern is a reverse image searching on maps, powered by a convolutional neural network: http://techcrunch.com/2016/05/25/terrapattern-is-a-neural-net-powered-reverse-image-search-for-maps/
A biased data set will give a biased model, even if the biases are racial/gender/cultural. Why is this still news? http://motherboard.vice.com/en_au/read/weve-already-taught-artificial-intelligence-to-be-racist-sexist
At least the US government is taking AI seriously. Will others? http://www.geekwire.com/2016/white-house-ai-workshop-focuses-machines-plus-humans-will-affect-government/
Why Python is such a good match for machine learning: http://www.analyticbridge.com/profiles/blogs/machine-learning-with-python-why-do-they-form-the-best
Something of a glossary of key machine learning terms: http://www.kdnuggets.com/2016/05/machine-learning-key-terms-explained.html
Amazon is expanding its cloud-based machine learning offerings: http://www.bloomberg.com/news/articles/2016-05-26/amazon-to-battle-google-with-new-cloud-service-for-ai-software

Friday, May 20, 2016

Weekly Review 20 May 2016

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

Three skills data scientists need: http://www.kdnuggets.com/2016/05/practical-skills-practical-data-scientists-need.html
A pathway to malevolent AI: http://www.techrepublic.com/article/creating-malevolent-ai-a-manual/
What to do if ANN error increases: http://www.kdnuggets.com/2016/05/troubleshooting-neural-network-error-increase.html
Deep learning ANN in self-driving cars: http://www.informationweek.com/mobile/mobile-devices/nvidia-car-learns-to-drive-by-watching-humans/d/d-id/1325460?
Reproducing van Gogh's painting style with deep learning neural networks: https://www.technologyreview.com/s/601424/algorithm-clones-van-goghs-artistic-style-and-pastes-it-onto-other-images-movies/
Machine learning system that gives the conditions for growing new types of crystals: http://futurism.com/machine-learning-uses-human-failures-to-make-crystals/
Do computers in classrooms lower exam performance? http://www.theregister.co.uk/2016/05/12/mit_study_finds_students_assisted_by_computers_do_worse_in_exams/
Speeding-up neural networks by doing fewer multiplications: http://arxiv.org/abs/1510.03009
On de-coupling peer review from specific journals: https://www.insidehighered.com/views/2016/05/16/why-not-make-academic-journal-acceptance-portable-essay
More about machine learning in materials science: http://nextbigfuture.com/2016/05/machine-learning-techniques-could.html
Perhaps open review would reduce the tendency that anonymous reviewers have to be dicks: https://www.insidehighered.com/views/2016/05/16/open-peer-review-journal-articles-offers-significant-benefits-essay
How long before these AI are writing student essays-for-hire? http://www.theverge.com/2016/5/15/11678142/google-ai-writes-fiction-natural-language-neural-network
First materials science, now an AI does physics: http://www.eurekalert.org/pub_releases/2016-05/anu-air051316.php?utm_source=dlvr.it&utm_medium=twitter
This article seems to be confusing Elm the programming language with ELM as in Extreme Learning Machines: http://www.valuewalk.com/2016/04/future-machine-learning/
An introduction to natural language processing, with some useful links to information and libraries: http://blog.algorithmia.com/2016/04/introduction-to-natural-language-processing/
Badder than a bad thing that's very, very bad: http://motherboard.vice.com/en_au/read/elsevier-buys-ssrn
I've certainly encountered my share of narcissists in academia: http://www.theguardian.com/education/2016/may/17/university-research-academic-bragging-grants
The case for randomly accepting borderline papers: http://www.kdnuggets.com/2016/05/embrace-random-acceptance-borderline-papers.html
How and why machine learning isn't enough in financial fraud detection: http://dataconomy.com/machine-learning-fraud-artificial-intelligence-isnt-enough/
Semi-supervised reinforcement learning: http://www.kdnuggets.com/2016/05/intro-semi-supervised-reinforcement-learning.html
Some resources on deep learning: http://www.datasciencecentral.com/profiles/blogs/deep-learning-definition-resources-comparison-with-machine-learni
How can we control an AI if nobody understands it? http://techcrunch.com/2016/05/16/how-can-we-control-intelligent-systems-no-one-fully-understands/
Twitter has developed an AI that can recognise what is happening in videos: https://www.technologyreview.com/s/601284/twitters-artificial-intelligence-knows-whats-happening-in-live-video-clips/
Seems like GoButler is offering a natural-language processing service for hire: http://techcrunch.com/2016/05/16/angel-ai/
Intelligent chatbots for banking customer service: https://www.technologyreview.com/s/601418/do-your-banking-with-a-chatbot/
Will machine learning bring about the end of coding? http://www.wired.com/2016/05/the-end-of-code/
Google has created its own ASIC chips to implement deep neural networks: http://www.wired.com/2016/05/google-tpu-custom-chips/
Claims that Google's deep neural network chip could advance Moore's law by 7 years: http://www.pcworld.com/article/3072256/google-io/googles-tensor-processing-unit-said-to-advance-moores-law-seven-years-into-the-future.html#comments
12 ways AI could disrupt the senior executives of a corporation: http://www.informationweek.com/big-data/12-ways-ai-will-disrupt-your-c-suite/d/d-id/1325557?
An overview of word2vec, encoding words to vectors: http://www.kdnuggets.com/2016/05/amazing-power-word-vectors.html
List of lists of resources on machine learning, deep learning, and natural language processing: http://www.datasciencecentral.com/profiles/blogs/curated-lists-of-data-science-machine-learning-deep-learning-and
A neural-network based approach for finding a photo that most matches a sketch: https://www.newscientist.com/article/mg23030742-600-scan-your-doodles-to-find-the-perfect-matching-photo-online/
Yahoo's meme-GIF making AI: http://motherboard.vice.com/en_au/read/these-fire-gifs-were-made-by-artificial-intelligence-yahoo
Some niche machine learning software projects: http://www.kdnuggets.com/2016/05/five-machine-learning-projects-cant-overlook.html
Google's Awareness API: http://www.theverge.com/2016/5/19/11712608/android-awareness-api-google-io-2016
Description of 3 clustering algorithms, k-means, EM clustering and Affinity Propagation: https://www.toptal.com/machine-learning/clustering-algorithms
Some supposed progress towards artificial general intelligence: http://nextbigfuture.com/2016/05/vicarious-will-show-off-their-progress.html

Computational Intelligence

Thursday, August 4, 2016

IEEE Transactions on Fuzzy Systems, Volume 24, Issue 1, 2016

Tuesday, August 2, 2016

Neural Networks, Volume 81, Pages: 1-102, September 2016

IEEE Transactions on Neural Networks and Learning Systems, Volume 27, Issue 8, August 2016

Saturday, July 9, 2016

Weekly Review 9 July 2016

Sunday, July 3, 2016

Review 12 June - 3 July

Saturday, July 2, 2016

IEEE Transactions on Neural Networks and Learning Systems;Volume 27, Issue 7, July 2016.

Sunday, June 12, 2016

Weekly Review 11 June 2016

Sunday, June 5, 2016

IEEE Transactions on Neural Networks and Learning Systems, Volume 27, Issue 6, June 2016

Saturday, June 4, 2016

IEEE Transactions on Fuzzy Systems, Volume 24, Issue 3

Weekly Review 3 June 2016

Saturday, May 28, 2016

IEEE Transactions on Evolutionary Computation, Volume 20, Number 3, June 2016

Weekly Review 27 May 2016

Friday, May 20, 2016

Weekly Review 20 May 2016

Pages

Google Website Translator Gadget

Search This Blog

Labels

Blog Archive

Thursday, August 4, 2016

Tuesday, August 2, 2016

Saturday, July 9, 2016

Sunday, July 3, 2016

Saturday, July 2, 2016

Sunday, June 12, 2016

Sunday, June 5, 2016

Saturday, June 4, 2016

Saturday, May 28, 2016

Friday, May 20, 2016

Pages

Google Website Translator Gadget

Subscribe To

Search This Blog

Labels

Blog Archive