PY 895 Machine Learning for Physicists. Fall 2018


This is the website for PY 895, Machine Learning for Physicists This website will be updated with HWs and suggested readings. In the fall, the class will be based on our new review A high-bias, low-variance introduction to Machine Learning for physicsits. Please use the link for the updated version that I will email you.

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 , PyTorch , TensorFlow

Syllabus and Course Information: pdf

Weeks 1: Chapter 1-2/ Notebook 1.

Other Viewing + Readings: 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

Weeks 2: Chapter 3 and 5.

Homework 1: This is Homework 1. Due on Tuesday Sept 17.

Weeks 3-4:Chapter 4 and 6.

Homework 2: This is Homework 2. Due on Tuesday Oct 2.

Weeks 5-7:Chapter 7 and 8.

Homework 3: This is Homework 3. Due on Tuesday Oct 23.

Weeks 7-9:Chapter 9-11.

Homework 4: This is Homework 4. Due on Tuesday Nov 13.

Weeks 9-11:Chapter 12-14

Homework 5: Please turn in two page summary of your final project (1 per group). Final projects will be due Monday Dec. 17th. Summary due on Thursday Nov 29.

Paper for class: Neal and Hinton EM paper.

Weeks 12-13:Chapter 15-16.

Homework 6: Notebook 16. Due on Thursday Dec 6th.
Paper for class:Boltzmann Encoded Adversarial Machines