SMS 00103335: Deep Learning and Reinforcement Learning
Fall 2026, Peking University
Info
Time: odd Mondays 13:00-14:50, Wednesdays 15:10-17:00, Room 206, Nature Sciences Teaching Building.
Office hour: Monday 15:10-17:00, Zhihua Building 341.
Teaching Assistant: Yutong Wang (1540622488 at qq dot com)
Office hour: x.
Midterm Exam: Nov x, 2026.
Final Exam: x.
Grading: Homework 40%, midterm exam 30%, final exam 30%.
Course Description
As highly successful and widely applied machine learning methods, deep learning and reinforcement learning are the core techniques underlying the latest major breakthroughs in the field of AI. Building on the general principles and methodology of machine learning and motivated by important practical problems, this course will introduce the basic concepts and methods, mathematical foundations and theory, optimization algorithms, and applications and case studies of deep learning and reinforcement learning. The part on deep learning will cover feedforward neural networks, regularization and optimization for deep learning, convolutional neural networks, recurrent neural networks, and autoencoders and generative models; the part on reinforcement learning will cover multi-armed bandits, Markov decision processes, dynamic programming, Monte Carlo methods, temporal difference learning, and deep reinforcement learning.
Reference
Markov Decision Processes and Reinforcement Learning, Martin L. Puterman and Timothy C. Y. Chan.
Convex Optimization: Algorithms and Complexity, Sébastien Bubeck
Foundations of Machine Learning, Mehryar Mohri, Afshin Rostamizadeh and Ameet Talwalkar
Deep Learning, Ian Goodfellow, Yoshua Bengio, Aaron Courville
Lectures
Lecture notes, update: 9.8
9.7: Introduction
9.9, 9.16: Stochastic optimization
Assignments
|