Course Information
Instructor
Dr. Tao Huang
Email
Office Hours
Monday 16:00-19:00
Class Time
Monday 12:55–15:40
Location
东上院 205
Language
English
Course Goals
- Understand what is AI and core AI principles.
- Master foundational ML and deep learning methods.
- Gain insight into modern AI paradigms: large models, generative models, RL, …
- Develop the ability to analyze, design, and evaluate AI systems.
Quick Links
Textbooks / References
- R&N Russell & Norvig, Artificial Intelligence: A Modern Approach
- DL Goodfellow et al., Deep Learning
- Papers Weekly reading links will be posted in schedule
Announcements
Welcome! This page will be updated weekly with slides, readings, and assignments.
Last updated:
Assessment & Coursework
Homework
40%
Project
40%
Presentation
10%
Participation
10%
Coursework
- Coursework 1: Route Planning with Search Algorithms (canvas)
Due:
2026-03-16, 23:59 CST - Coursework 2: Classification: Logistic Regression (canvas)
Due:
2026-04-13, 23:59 CST - Coursework 3: Classification: MLP (canvas) Due: 2026-04-27, 23:59 CST
- Coursework 4: Classification: Logistic Regression (canvas) Due: 2026-05-11, 23:59 CST
- Final Project: Multimodal Classification Challenge (presentation requirements)
Group registration: 2026-05-29, 23:59 CST · Leaderboard closes: 2026-06-12, 20:00 CST · Code + report + slides: 2026-06-14, 23:59 CST
Schedule (16 Weeks)
| Week | Date | Topics | Slides | Extra Materials | Coursework |
|---|---|---|---|---|---|
| Module 1: Introduction | |||||
| 1 | 2026-03-02 |
Introduction to AI 1. What is AI? 2. History of AI 3. Modern AI Landscape 4. Weak AI vs. AGI |
L1 | — | — |
| Module 2: Search | |||||
| 2 | 2026-03-09 |
Search Algorithms 1. Uninformed Search 2. Informed Search 3. Heuristic Search & A* |
L2 • L3 • L4 | — |
Coursework 1 Search Algorithms (canvas) Due: |
| 3 | 2026-03-16 |
Beyond Basic Search 1. Local Search 2. Adversarial Search 3. Constraint Satisfaction |
L5 • L6 • L7 | — | — |
| Module 3: Machine Learning | |||||
| 4 | 2026-03-23 |
Supervised Learning 1. Machine Learning Paradigm 2. Linear Models 3. Optimization |
L8 • L9 • L10 | — | — |
| 5 | 2026-03-30 |
Classical ML 1. Support Vector Machines 2. Decision Trees & Ensemble Methods 3. Model Evaluation |
L11 • L12 • L13 | Extra_reading: Hyperparameter Optimization |
Coursework 2 Logistic Regression (canvas) |
| Module 4: Deep Learning | |||||
| 6 | 2026-04-13 |
Neural Networks 1. Perceptron & MLP 2. Backpropagation 3. Training Deep Networks |
L14 • L15 • L16 | Extra_reading: Gradient Checkpointing |
Coursework 3 MLP (canvas) Due: 2026-04-27, 23:59 CST |
| 7 | 2026-04-20 |
CNNs & Vision 1. Convolutional Neural Networks 2. Modern CNN Architectures 3. Self-Supervised Learning |
L17 • L18 • L19 | Extra_reading: Structured Pruning |
Coursework 4 CNN (canvas) Due: 2026-05-11, 23:59 CST |
| 8 | 2026-04-27 |
Sequence Models & Transformers 1. RNN & LSTM 2. Attention Mechanism 3. Transformers |
L20 • L21 • L22 | Extra_reading: Efficient Attention | — |
| Module 5: Generative AI | |||||
| 9 | 2026-05-09 |
Generative Models 1. Probabilistic Generative Modeling 2. Variational Autoencoders 3. Generative Adversarial Networks |
L23 • L24 • L25 | Extra_reading: Discrete Tokenizer & Visual AR | — |
| 10 | 2026-05-11 |
Diffusion & Multimodal Generation 1. Diffusion Models 2. Large Language Models 3. Vision-Language Models |
L26 • L27 • L28 | Extra_reading: Flow Matching & DiT | — |
| Module 6: Reinforcement Learning | |||||
| 11 | 2026-05-18 |
RL Foundations 1. Markov Decision Processes 2. Dynamic Programming 3. Temporal Difference Learning |
L29 • L30 • L31 | Extra_reading: Gaming AI |
Final project released Form your team and skim the handout. |
| 12 | 2026-05-25 |
Deep RL & Policy Learning 1. Deep Q Networks 2. Policy Gradient Methods 3. Model-Based RL |
L32 • L33 • L34 | Extra_reading: The post PPO era |
Final Project Group registration Due: 2026-05-29, 23:59 CST |
| Module 7: Embodied & Frontier AI | |||||
| 13 | 2026-06-01 |
AI Agents 1. Tool-Using LLM Agents 2. Long-Horizon Reasoning 3. Autonomous Systems |
L35 • L36 • L37 | — | — |
| 14 | 2026-06-08 |
Embodied Intelligence & Robotics 1. Perception-to-Action Models 2. Sim-to-Real Challenges 3. Robotics Foundation Models |
L38 • L39 • L40 | — |
Final Project Leaderboard closes Fri 2026-06-12, 20:00 CST Final zip on Canvas Sun 2026-06-14, 23:59 CST |
| 15 | 2026-06-15 |
Presentation Week 1. Final Project Presentations 2. Presentations, Q&A, and feedback 3. Course synthesis & future outlook 15-week semester — last class meeting |
— |
Final Project Presentations 8 min talk + Q&A · all members speak |
|