PY 895 Machine Learning for Physicists. Fall 2020

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 review A high-bias, low-variance introduction to Machine Learning for physicsits. The review can be downloaded from the arXiv or Physics Reports if for some reason you prefer that formatting. The Jupyter Notebooks can be downloaded from Github.

General course information: TTh 9:30-11:00. SCI B58 + Zoom (email for info).

Installing Python:

The easiest way to install Python is using the Anaconda distribution: Anaconda.
Please also install Jupyter Notebooks and/or Jupyter Lab: Jupyter.

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 1-4/ Notebook 1-2.

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 2-4: Chapter 5-6/ Notebook 3-4.

Please turn in indicated notebooks.

Weeks 5-7: Chapter 7/ Notebook 5-7

Please turn in indicated notebooks.

Weeks 6-8: Chapter 9-11/ Notebook 11-14

Please turn in Notebooks 12+14 by October 28th. Optional (11,13)

Weeks 9: More on supervised learning

Other Viewing + Readings: Paper on bias and variance in overparameterized models. Also these slides giving overview of some modern supervised learning methods.

Weeks 10: Chapter 12. Dimensional Reduction

Other Viewing + Readings: Visualizing PCA, tSNE, and UMAP with embedding projector.