# CS 536: Machine Learning (Spring 2020) <!-- ## Overview The principal purpose of this course is to introduce the student to the problems of pattern recognition through a comparative presentation of methodology and practical examples. The course particularly emphasize probabilistic approaches to pattern recognition and machine learning. The course is intended for computer science students with an applied mathematics orientation, and also for students in other programs (computer and electrical engineering, statistics, mathematics, psychology) who are interested in this area of research. --> ## Topic Overview The following topics are expected to be covered (topics are tentative): - Basicis of Machine Learning and Probabilistic Learning - Probabilistic Graphical Models - Deep Learning - Reinforcement Learning <!-- Basic ML concepts, Gaussian Models, Bayesian/Frequentist Learning, Linear Regression, Logistic Regression, Artificial Neural Networks, Mixture Models, Expectation-Maximization, Dimensionality Reduction, Kernel Methods, Support Vector Machines, Gaussian Processes, Recommender Systems, Decision Trees, Boosting, etc. --> ## Instructor & TA - Instructor - Sungjin Ahn (sungjin.ahn@cs.rutgers.edu) at CBIM-07 - Teaching Assistant - TBD ## Time and Location <!-- - When: Tuesday and Thursday at 3:20pm - 4:40pm, from Sep. 3 to Dec. 5 - Where: CCB 1203 --> ## Office Hours <!-- - TA office hour: 4~5PM on Friday (CBIM) - Instructor office hour: 9:30~10:30am on Friday (CBIM 9) --> ## Pre-Requisites - 16:198:530 or 16:198:520 - Requesting SPN [[link]](https://secure.sas.rutgers.edu/apps/special_permission/cs) ## Textbooks 1. [Pattern Recognition and Machine Learning (PRML)](https://www.microsoft.com/en-us/research/uploads/prod/2006/01/Bishop-Pattern-Recognition-and-Machine-Learning-2006.pdf), Christopher C. Bishop, Springer, 2006 1. Deep Learning (DL), Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron, MIT Press, 2016 2. [Reinforcement Learning](http://incompleteideas.net/book/RLbook2018.pdf), Andrew Barto, Richard S. Sutton Optional - Machine Learning: A Probabilistic Perspective (MLPP), Kevin P. Murphy, MIT Press, 2012 ## Resources <!-- - [Canvas](https://rutgers.instructure.com/courses/33622) - [Lecture Slides](https://drive.google.com/drive/folders/1jo351ilxtITYu7vxTnIFoM-z4pqOtWVo?usp=sharing) --> ## Grading <!-- (The following percentage can be adjusted) - Midterm/Quiz (30%) - Final Exam (30%) - Final Projects (40%) --> ## Schedule <!-- 1. 09/03 - Basic Concepts 2. 09/05 - Basic Concepts 3. 09/10 - Basic Concepts & Fundamentals of Probabilistic Learning 1 4. 09/12 - Fundamentals of Probabilistic Learning 2 5. 09/17 - Fundamentals of Probabilistic Learning 3 6. 09/19 - Fundamentals of Probabilistic Learning 4 7. 10/01 - Linear Models for Regression 1 8. 10/03 - Linear Models for Regression 2 9. 10/08 - **Quiz** 10. 10/10 - Linear Models for Classification 1 11. 10/15 - Linear Models for Classification 2 12. 10/17 - Deep Learning - MLP 13. 10/22 - Deep Learning - CNN 14. 10/24 - Deep Learning - RNN 15. 10/29 - Deep Learning - RNN cont. & Attention 16. 10/31 - Kernel Methods - Support Vector Machines 1 17. 11/05 - Kernel Methods - Support Vector Machines 2 & Gaussian Processes 1 18. 11/07 - Kernel Methods - Gaussian Processes 19. 11/12 - Mixture Models and EM 20. 11/14 - Mixture Models and EM 21. 11/19 - (tentative) Decision Trees, Boosting, PCA 22. 11/21 - **Final Exam** 23. 11/26 - (tentative) Decision Trees, Boosting, PCA 24. ~~11/28~~ - Thanksgiving Break 25. 12/03 - **Project Presentation 1** 26. 12/05 - **Project Presentation 2** --> <!-- ## [Final Exam (On Nov 21)](https://hackmd.io/0GOhywPUS2i-hrkyOFnbZw?both) --> <!-- ## [Final Project](https://hackmd.io/@Tn97A1U0QG6gBtFPXRh4oQ/r1xhzryqS) -->