About

Table of contents

1. Course Description
2. Course Syllabus
   1. AI Policy for the Deep Learning course
3. Reference
   1. Courses:
   2. Books

---

Course Description

This course provides a hands-on introduction to modern deep learning, moving from core concepts (tensors, optimization, and neural network training) to practical model families used across science and industry.

Students will build intuition and implementation skills in PyTorch, study key architectures including MLPs, CNNs, autoencoders, GANs, autoregressive models, and transformers.

The course also connects these methods to real-world applications in computer vision, natural language processing, and large language models, with attention to efficient inference and post-training workflows.

Course Syllabus

Here is the Course Syllabus

AI Policy for the Deep Learning course

Students are permitted to use AI assistants for all homework and programming assignments (especially as a reference for understanding any topics that seem confusing), but we strongly encourage you to complete your final submitted version of your assignment without AI.

Reference

Courses:

• CMU deep learning fall 2025
• Stanford, deep learning 6.S19
• MIT, deep learning 6.S19
• Cornell, Intro to Deep Learning, Spring 2025

Books

• Dive Into Deep Learning, by Zhang, A., Lipton, Z.C., Li, M. & Smola, A.J. This text is available online. Book website

This text includes many of the topics covered in this course with instructive Pytorch implementations. We will provide section numbers to this text alongside many of the lectures (abbreviated as DiDL in the schedule).