PY 895 Machine Learning for Physicists. Fall 2016


 


This is the website for PY 895, Machine Learning for Physicists This website will be updated with HWs and suggested readings.


General course information: TTh 9:30-11:00.


Useful Resources:

David Mackay's Information Theory, Inference, and Learning Algorithms.

Abu Mustafa's Online Course: Learning from Data

Michael Neilsen's Neural Networks and Deep Learning

Python Packages: Python scikit-learn Library


Syllabus and Course Information: pdf


Weeks 1-3: Suggested Viewing + Reading: Lectures 1-3 from Learning from Data. Chapters 1-3 of Information Theory, Inference, and Learning Algorithms. IPython Cookbook fourth feature recipe: Introduction to Machine Learning in Python with scikit-learn


Python Notebook 1 : Prediction is difficult- Download or look at html.


Week 4-5: Suggested Viewing + Reading: Bishop Pattern Recognition Chapters 3+4; See also resources here from Metacademy: Linear Regression. Also, check out the relevant Python packages and explanations at Generalized Linear Models.

Video: Michael Jordan Bayesian of Frequentist, Which are you?

Python Notebook 2: Understanding regularization- Download or look at html.


Week 6-7: Suggested Viewing + Reading: Bishop Pattern Recognition Chapters 9 and Chapter 20, 22 of MacKay.

Python Notebook 4: K-means Clustering Download.


Week 7-9: Suggested Viewing + Reading: Bishop Pattern Recognition Chapters 10 and Chapter 34 of MacKay. Also see this beautiful review of Yedida and collaborators.


Week 10-11: Suggested Viewing + Reading: Chapter 42+43 of MacKay. The amazing Hopfield paper. Geoff Hinton's practical guide to training RBMs. Also see this beautiful review of Yedida and collaborators.

HOMEWORKS

Homework 1: HW1 Due Thursday Oct 6th

Homework 2: HW2 also as Notebook: Download Due Tuesday Oct 18th

Homework 3: HW3 Due Tuesday Nov 28th