08408005 Deep Learning: Algorithm and Application
AAIS, Peking University
Spring 2022

Instructor:

Teaching Assistant:

Location: Room 105, Teaching Building 3, Peking University

Time: Tuesday 10:10am - 12:00pm (weekly), Thursday 10:10am - 12:00pm (biweekly)

Office hours: Drop an email or wechat message to the instructor or TAs for appointing a course-related face-to-face QA.


Schedule of Lectures

Date Topics
Feb 22, 2022 Introduction
  • Course logistics
  • A short tour to deep learning: illustrative applications, brief history etc.
March 1, 2022 Machine Learning Basics
  • Machine learning paradigms
  • Supervised learning: linear case
  • Supervised learning: non-linear case
  • Gradient Descent
  • Stochastic Gradient Descent
  • Unsupervised learning
March 3, 2022 Deep Learning Basics
  • Neural layers: convolution, pooling, FC, activation, loss functions
  • Gradient back-propagation
  • Auto-differentiation
  • Regularization
March 8, 2022 Backbone - I
March 15, 2022 Backbone - II
March 17, 2022 Backbone - III
March 22, 2022 Sequential Models
March 29, 2022 Transformer and MLP-Mixer
March 31, 2022 Generative Models
April 5, 2022 Holiday - no class
April 12, 2022 Adversarial and Backdoor Learning
April 14, 2022 Deep Learning on Graphs Invited speaker: Professor Wei Hu from Wangxuan institute of Computer Technology, Peking University
April 19, 2022 Self-Supervised Learning / Meta-Learning / Continual Learning
April 26, 2022 Reinforcement Learning - I
April 28, 2022 Reinforcement Learning - II
May 3, 2022 Holiday - no class
May 10, 2022 Deep Learning for Optimization
May 12, 2022 Neural Architecture Search
May 17, 2022 Applications: Computer Vision
May 24, 2022 Applications: Robotics
May 26, 2022 Applications: Natural Language Processing Invited speaker: Professor Yansong Feng from Wangxuan institute of Computer Technology, Peking University
May 31, 2022 Course Project Presentation - I To be announced
June 7, 2022 Course Project Presentation - II To be announced
June 9, 2022 Course Project Presentation - III To be announced


Textbook:

References:


Course Work

Final Grade
  • Grading will be based on homeworks (25%), survey (25%) and a course project (50%).
  • The end-of-term grade is curved. Your overall grade will depend on your performance relative to your classmates.
Survey & Project
  • The topic of survey paper should be DL-related.
  • A Course Project is mandatory for all students. The only requirement for the topic is being deep learning related.