Resources on Machine Learning =================================================================== Class: Topics in Social Media Weka tutorials: --------------------------------------------------------------------------------------------------- http://machinelearningmastery.com/how-to-run-your-first-classifier-in-weka/ http://www.ibm.com/developerworks/opensource/library/os-weka1/index.html http://www.ibm.com/developerworks/opensource/library/os-weka2/index.html http://www.ibm.com/developerworks/opensource/library/os-weka3/index.html Weka Course and associated Videos: --------------------------------------------------------------------------------------------------- https://weka.waikato.ac.nz/dataminingwithweka/preview https://www.youtube.com/watch?v=Exe4Dc8FmiM Feature Selection to Improve Accuracy and Decrease Training Time --------------------------------------------------------------------------------------------------------- http://machinelearningmastery.com/feature-selection-to-improve-accuracy-and-decrease-training-time/ Machine Learning Ontology: --------------------------------------------------------------------------------------------------- http://www.datascienceontology.com/ Tutorials and videos for further learning: --------------------------------------------------------------------------------------------------- http://www.toptal.com/machine-learning/machine-learning-theory-an-introductory-primer http://machinelearningmastery.com/how-to-build-an-intuition-for-machine-learning-algorithms/ http://www.dataschool.io/15-hours-of-expert-machine-learning-videos/ http://openclassroom.stanford.edu/MainFolder/CoursePage.php?course=MachineLearning https://wakelet.com/wake/atfflSHf5/data-science Videos: --------------------------------------------------------------------------------------------------- sentiment analysis: https://www.youtube.com/watch?v=ytUHvMNnzZk advertising application: https://www.youtube.com/watch?v=EQhwNcQhP4g Reinforcement Learning: https://www.youtube.com/watch?v=xM62SpKAZHU * * Neural Networks - Deep dream: http://googleresearch.blogspot.com/2015/06/inceptionism-going-deeper-into-neural.html http://motherboard.vice.com/read/why-googles-neural-networks-look-like-theyre-on-acid http://rhizome.org/editorial/2015/jul/10/deep-dream-doggy-monster/ Google Tensorflow (Machine learning engine that is open source) --------------------------------------------------------------------------------------------------- https://hacked.com/meet-googles-new-open-source-machine-learning-tool-tensorflow/ Writings On Machine Learning Algorithms: --------------------------------------------------------------------------------------------------- *Louder vowels won’t get you laid, and other tales of spurious correlation *http://arstechnica.com/science/2015/06/louder-vowels-wont-get-you-laid-and-other-tales-of-spurious-correlation-2/ *Politique des Algorithmes (in French and in English) *http://www.scoop.it/t/politique-des-algorithmes Deep Learning: --------------------------------------------------------------------------------------------------- *Goofy Deep Learning Video: *https://www.youtube.com/watch?v=bHvf7Tagt18 Google's Deep Dream Project: * *Blog Post by Google: Inceptionism: Going deeper into Neural Networks *http://googleresearch.blogspot.co.uk/2015/06/inceptionism-going-deeper-into-neural.html *Deep Dream Code on Github: *https://github.com/google/deepdream *http://googleresearch.blogspot.com/2015/07/deepdream-code-example-for-visualizing.html *Yes, androids do dream of electric sheep *http://www.theguardian.com/technology/2015/jun/18/google-image-recognition-neural-network-androids-dream-electric-sheep *And how it might be used: *https://gigaom.com/2013/09/13/why-machine-learning-might-be-a-wearable-cameras-best-friend/ * *Google and Spam: *http://www.csmonitor.com/Technology/2015/0713/Google-fights-spam-with-artificial-intelligence * Algorithms of the Mind: What machine learning teaches us about ourselves? https://medium.com/deep-learning-101/algorithms-of-the-mind-10eb13f61fc4 Computer Science Paper: Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images *http://arxiv.org/abs/1412.1897 * *The unreasonable effectiveness of Recurrent Neural Networks *https://karpathy.github.io/2015/05/21/rnn-effectiveness/ Statistics vs. Machine Learning: --------------------------------------------------------------------------------------------------- *The two cultures: statistics vs. machine learning *http://stats.stackexchange.com/questions/6/the-two-cultures-statistics-vs-machine-learning *http://econometricsense.blogspot.com/2011/01/classical-statistics-vs-machine.html * *Ramsay (2003: 173) notes, when one is not looking for a ‘right’ classification but for an ‘interesting’ pattern, many of the traditional statistical measures of evaluation are of little use: ‘Empirical validation and hypothesis testing simply make no sense in a discourse where the object is not to be right (in the sense that a biologist is ever “right”), but to be interesting (in the sense that a great philosopher is “interesting”)'. * Machine Learning vs. Artificial Intelligence: --------------------------------------------------------------------------------------------------- https://www.youtube.com/watch?v=WXHM_i-fgGo Fiction: --------------------------------------------------------------------------------------------------- Speak - A novel by Louisa Hall on artificial intelligence: http://www.harpercollins.com/9780062391193/speak/web-sampler absolute geekiness on overfitting: --------------------------------------------------------------------------------------------------- https://www.youtube.com/watch?v=fJMXDlNkYvU Torch7 --------------------------------------------------------------------------------------------------- Torch7 is an easy to use MATLAB-like environment for machine learning applications. It uses lua, a simple scripting language, and underlying C with GPUs (CUDA) for fast, parallel processing. Code & README: https://github.com/torch/torch7 NYU CILVR Lab's Page: http://cilvr.nyu.edu/doku.php?id=software:torch:start Tutorial: http://code.madbits.com/wiki/doku.php?id=tutorial Microsoft's Distributed Machine Learning Toolkit --------------------------------------------------------------------------------------------------- http://www.dmtk.io/ Fun Examples --------------------------------------------------------------------------------------------------- How the delivery service Postmates estimates delivery times: http://engineering.postmates.com/Estimating-Delivery-Times/ Analyzing live movement: http://blog.telenor.io/2015/10/26/machine-learning.html Rap lyrics generator using maching learning: http://www.deepbeat.org/ Identifying author of an email: http://blog.brainattica.com/machine-learning-for-indentify-the-author-of-an-email/ Google Smart Reply uses neural networks to write probable email responses for you: http://googleresearch.blogspot.com/2015/11/computer-respond-to-this-email.html