├── README.md ├── _config.yml └── slides ├── lec1.pdf └── lec2.pdf /README.md: -------------------------------------------------------------------------------- 1 | # A Whirlwind Tour of ML 2 | ###_IAP 2017 course at MIT_ 3 | 4 | ## About 5 | This course gives a high-level overview of diverse areas of machine learning. The goal is to introduce students to core concepts and techniques in ML, and provide enough of a primer on different sub-areas of ML so that students can choose the right approach for a given problem and explore interesting topics further. 6 | 7 | The course covers an introduction to ML, Inference, Bayesian Methods and Neural Networks. Each class is taught by graduate students or post-docs at MIT working in the specific areas. 8 | 9 | Organized by [Manasi Vartak](http://people.csail.mit.edu/mvartak/) and [Maggie Makar](http://mmakar.scripts.mit.edu/mmakar/) from MIT CSAIL. 10 | 11 | ## Session I: Introduction to ML 12 | This session gives an overview of supervised and unsupervised learning, and an introduction to probabilistic graphical models. 13 | 14 | _Concepts_: Loss functions, Linear regression, Logistic regression, SVMs, Decision trees, Random Forests, Clustering, PCA, Graphical Models, Variable Elimination 15 | 16 | Taught by [Manasi Vartak](http://people.csail.mit.edu/mvartak/). 17 | 18 | ### [Slides](slides/lec1.pdf) 19 | ### Resources 20 | - [MIT 6.867 Machine Learning](https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-867-machine-learning-fall-2006/) 21 | - [Coursera Machine Learning](https://www.coursera.org/learn/machine-learning) 22 | - [MIT 9.520 Statistical Learning Theory](http://www.mit.edu/~9.520/fall16/) 23 | - [CMU: Intro to Machine Learning](www.cs.cmu.edu/~epxing/Class/10701/) 24 | - [Michael Jordan Review of Graphical Models](https://www.cs.cmu.edu/~aarti/Class/10701/readings/graphical_model_Jordan.pdf) 25 | - [Coursera Probabilistic Graphical Models](https://www.coursera.org/learn/probabilistic-graphical-models/home) 26 | - [Columbia University: Probabilistic Graphical Models](http://www.cs.columbia.edu/~blei/fogm/2016F/) 27 | 28 | ## Session II: Inference 29 | This session gives an overview of (approximate) inference for probabilistic graphical models. 30 | 31 | _Concepts_: Gaussian Mixture Models, Variational Inference, Monte Carlo Sampling 32 | 33 | Taught by [Maggie Makar](http://mmakar.scripts.mit.edu/mmakar/) 34 | ###[Slides](slides/lec2.pdf) 35 | ### Resources 36 | - [Tutorial on VI](http://digitalassets.lib.berkeley.edu/techreports/ucb/text/CSD-98-980.pdf) 37 | - [A Review of recent work on VI](https://arxiv.org/pdf/1602.05221v2.pdf), Section 5 38 | - [Tutorial on Sampling methods](http://www.cs.ubc.ca/~arnaud/andrieu_defreitas_doucet_jordan_intromontecarlomachinelearning.pdf) 39 | - [A review (and really cool demos) of recent work on sampling](http://chifeng.scripts.mit.edu/stuff/mcmc-demo/) 40 | 41 | ## Session III: Bayesian Methods 42 | This session gives a whirlwind tour of Bayesian Methods in ML. 43 | 44 | _Concepts_: What does it mean to be Bayesian in ML, Why be Bayesian, Posterior Inference, Parameteric vs. Non-Parametric Bayes 45 | 46 | Taught by [Trevor Campbell](http://trevorcampbell.me/) 47 | ###[Slides](https://docs.google.com/presentation/d/1qSYB8iDMIEInr0b4pn2M4Q0fSyFzyCBKFmO7j-6oLmM/edit#slide=id.p) 48 | ### Resources 49 | See slides! 50 | 51 | ## Session IV: Neural Networks 52 | This session gives an overview of neural networks, particularly as applied to computer vision. 53 | 54 | _Concepts_: Neural Nets, Convolutional NNs, AlexNet, GoogleLeNet, Transfer learning 55 | 56 | Taught by [Carl Vondrick](http://web.mit.edu/vondrick/) 57 | ###[Slides](http://6.869.csail.mit.edu/fa15/lecture/6.869-DeepLearningApplications3.pdf) 58 | Note: these slides are not exactly the ones that were presented in class. Please feel free to reach out to Carl if you need information that's not in these slides. 59 | -------------------------------------------------------------------------------- /_config.yml: -------------------------------------------------------------------------------- 1 | theme: jekyll-theme-tactile -------------------------------------------------------------------------------- /slides/lec1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mitdbg/ml-class-iap2017/5874f39f78c2a01cf0a170f73884357aaa0002b8/slides/lec1.pdf -------------------------------------------------------------------------------- /slides/lec2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mitdbg/ml-class-iap2017/5874f39f78c2a01cf0a170f73884357aaa0002b8/slides/lec2.pdf --------------------------------------------------------------------------------