---

---

Machine Learning in Physics

This is to facilitate the “Machine Learning in Physics” course that I am teaching at Sharif University of Technology for winter-21 semester. For more information, see the course page at

http://sharif.edu/~sraeisi/ML

---

Classes

We have our sessions on Saturday and Monday, 15-16.30 Tehran time (GMT+3:30).

The course is presented on online and the link of the class is:

https://vc.sharif.edu/ch/sraeisi

---

Reading Materials

• Raeisi, S., & Raeisi, S. (2023). Machine Learning for Physicists: A hands-on approach. IOP Publishing.

• Mehta, Pankaj, et al. "A high-bias, low-variance introduction to machine learning for physicists." Physics Reports (2019).

• Nielsen, Michael A. Neural networks and deep learning. Vol. 25. San Francisco, CA, USA:: Determination press, 2015. (Available online )

• Chollet, Francois. Deep learning with Python. Simon and Schuster, 2021.

• Albon, Chris. Machine learning with python cookbook: Practical solutions from preprocessing to deep learning. " O'Reilly Media, Inc.", 2018.

• Stevens, Eli, Luca Antiga, and Thomas Viehmann. Deep Learning with PyTorch. Manning Publications, 2020.

Assignments

Assigment	Deadline and Submission link	Solutions
A1: Problem statement	Mehr 10th
A2: Data	Mehr 24th
A3: Model, Loss & Optimization	Aban 8th
A4: Optimization & Model Evaluation	Azar 5th

---

Course Materials

The course material is posted here. If you come across a mistake or problem, please let me know.

Also, the videos of some(most) of the lectures are posted here. These videos are in Farsi.

Topic	Lecture notes	Notebook(s)	Videos
Section 1	Basics of Machine Learning
Introduction	Introduction to ML		Video 1 Video 2 Video 3
Data	Data		Video 1 Video 2
Model	Model		Video 1 Video 2 Video 3
Loss Functions	Loss Functions		Video 1 Video 2
Optimization	Optimization		Video 1 Video 2 Video 3
Model Evaluation	Model Evaluation		Video 1 Video 2 Video 3 Video 4
Section 2	Neural Networks
Introduction: Feed Forward	Introduction		Video 1 Video 2
Back Propagation	Back Propagation		Video 1 Video 2
NN Libraries			Video 1 Video 2
Examples: Model Evaluationa & Tuning
Section 3	More on Neural Networks
Convolutional Neural Networks	Convolutional Neural Networks
Implementation of CNN
Transfer Learning
Recurrent Neural Networks	Recurrent Neural Networks

---

Project

Milestone	Due date	Submission Link
Data	Mehr 30th	Submit here.
Traditional ML techniques	Aban 30th	Submit here.
Neural Networks: Same as MS2 but with NN	Azar 30th	Submit here.

---

Marking Scheme

This is a tentative plan and we may change it as we move on.

• Course Project: 40-60%

• Assignments: 20-40%

• Exam: 0-30%

• Class Participation 5-10%

---

Requirements:

• Decent understanding of programming and python and the following libraries

  • Numpy

  • Pandas

  • Plotting and graphical presentation tools in python

• Git and Github (if you not familiar, let me know.)

• Basic understanding of quantum mechanics and statistics.

• Basic understanding of machine learning

---

Cheat sheets and guides

See the files in the CheatSheet folder.

Item	Description
Jupyter	Jupyter provides an interactive environment for programming. We will be mostly using the python 3 kernel.
Git and Github	Git provides a strong infrastructure for version control. Github is web-based hosting service for version control and it also provides services for collaboration.
Python	It is the programming language that we will be mostly using for this course.
NumPy	It’s a python library that provides strong and efficient tools for manipulation of high-dimensional arrays.
SciPy	It’s a python library, built on NumPy for mathematical and scientific computing.
Pandas_basics Pandas 2 Importing data	It’s a python library, built on NumPy that provides efficient tools for handling and analysis of data.
Matplotlib Seaborn	These are two of the most common python library for visualization.
Scikit-Learn	It’s a python library that provides a nice and fairly efficient implementation of most the machine learning techniques and ideas.
Keras	It is python library that provides a high-level and easy-to-use interface for Tensorflow and some other deep learning libraries.