Artificial Intelligence (Fall 2024)

Artificial Intelligence (Fall 2024)

Course Information

Overview

Artificial Intelligence (AI) is about designing algorithms that enable machines to either behave like humans or assist humans in solving complex problems. In this course, we will explore several fundamental tools that help achieve these goals, including search, logical reasoning, statistical learning, and reinforcement learning. Additionally, we will discuss recent advance in generative AI, along with the associated safety and ethical issues.

Prerequisites

Grading

Late policy for assignments: Seven late days can be used for free in the whole semester. Each additional late day will result in a 10% deduction in the semester’s assignment grade. No assignment can be submitted more than seven days after its deadline.

Platforms

Discussions: Piazza
Homework submissions: Gradescope

Schedule (tentative)

Date Topics Slides and Recommended Reading Notes
8/27 History of AI Slides, History of AI, Sparks of AGI  
8/29 Search: BFS, DFS Slides, Slides(ppt), Ch 3 of AIMA  
9/3 Search: UCS   HW1 out
9/5 Search: Greedy, A*    
9/10 Search in Games: α-β pruning Slides, Slides(ppt), Ch 5 of AIMA  
9/12 Search in Games: Expectimax, MCTS    
9/17 Constraint Satisfaction: Backtracking search, forward checking Slides, Slides(ppt), Ch 6 of AIMA HW1 due on 9/16
HW2 out
9/19 Constraint Satisfaction: Arc consistency, ordering, local search    
9/24 Logic: Propositional logic, model checking Slides, Ch 7 of AIMA  
9/26 Logic: Forward inference, modus ponens, resolution    
10/1 Logic: First-order logic Ch 8,9 of AIMA HW3 out
HW2 due on 9/30
10/3 Probabilistic Models: Probability basics Slides, Ch 12 of AIMA  
10/8 Bayesian Network: Conditional independence, D-separation Slides, Ch 13 of AIMA  
10/10 Midterm Review Slides HW3-Choices due on 10/9 (late submission is not allowed)
10/15 Fall Reading Day    
10/17 Midterm Exam    
10/22 Bayesian Network: Variable elimination, rejection sampling, likelihood weighting, Gibbs sampling (continuing the 10/8 slides)  
10/24 Hidden Markov Model Slides, Slides(ppt), Ch 14 of AIMA  
10/29 Hidden Markov Model: Forward-backward algorithm, Viterbi algorithm, particle filtering   HW3-Programming due on 10/28
HW4 out
10/31 Machine Learning: Naive Bayes Slides, Ch 12.6, 19 of AIMA  
11/5 Election Day    
11/7 Machine Learning: Regularization, logistic regression, SGD Ch 20 of AIMA  
11/12 Deep Learning: Neural network Slides, Ch 21 of AIMA HW4 due on 11/11
11/14 Deep Learning: Training Neural network, CNN, RNN   HW5 out
11/19 Application: Computer Vision
(Guest lecture by Prof. Zezhou Cheng)		 Slides, Ch 25 of AIMA  
11/21 Application: Natural Language Processing
(Guest lecture by Prof. Yu Meng)		    
11/26 Reinforcement Learning    
11/28 Thanksgiving    
12/3 Reinforcement Learning   HW5 due on 12/2
12/5      
12/17 Final Exam (2-5pm)    

Books

AI Courses at Other Institutions

Acknowledgement

CYW would like to thank Prof. Yen-Ling Kuo for sharing her experiences and materials for this course. A lot of course materials are taken from Berkeley CS188, Stanford CS221, and MIT 6.034. The programming assignments are taken from Berkeley CS188.