CS 343H: Artificial Intelligence: Honors

Resources

This page preserves supplemental materials from a previous offering. For Fall 2026, the course is organized into background review, deterministic search, probabilistic search, probabilistic modeling, and deep learning. Use the Canvas timetable for the current sequence, lecture materials, and dates.

Reference sequence	Lectures and Exercises	Additional Resources
Week 1	Introduction, AI Ethics [Introduction] [AI: Ethics and Society]	Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. Stan Franklin and Art Graesser Forum for Artificial Intelligence: AI and Life in 2030 (to view, log in using your CS account) Information on pair programming; A video Rodney Brooks' dated predctions regarding the future of AI The Good Systems project at UT Austin
Week 2	Search [Search I] [Search II]	Sven Koenig's site on LPA* and D* lite Andrew Ng's A* search notes A student found this A* tutorial useful Related research papers Online Learning of Search Heuristics Bidirectional Search That Is Guaranteed to Meet in the Middle AlphaGo's Nature paper AlphaGo Zero
Week 3	Constraint Satisfaction Problems and Local Search [CSPs I] [CSPs II + Local Search]	Continuous state space learning on Aibos: walking; ball control GA applications Genetic Mona Lisa Path search in continuous environments using RRT's. Related research papers A constraint-based method for solving sequential manipulation planning problems Randomized algorithm for informative path planning with budget constraints
Week 4	Adversarial Search, Utilities [Adversarial Search] [Utilities]	Guide on pruning Some adversarial reasoning in the 2010 Super Bowl And some more from the 2012 Super Bowl The University of Alberta GAMES group The Berkeley GamesCrafters group A paper showing PacMan is NP-hard A slashdot discussion on it. A video about loss aversion and risk assessment by people Related research papers Evolutionary Many-Objective Optimization Based on Adversarial Decomposition Playing Multi-Action Adversarial Games: Online Evolutionary Planning versus Tree Search Starting at minute 10 of this video is a keynote by Mike Bowling on game playing AI, featuring their recent computer poker victory against people.
Week 5	Markov Decision Processes [MDPs I] [MDPs II]	Side-Stepping of the Triple Pendulum on a Cart Theory of Generalization: How an infinite model can learn from a finite sample Related research papers Learning a reward function: Inverse Reinforcement Learning Graph-based Cross Entropy method for solving multi-robot decentralized POMDPs Dynamically Constructed (PO) MDPs for Adaptive Robot Planning
Week 6	Reinforcement Learning [Reinforcement Learning I]	The Berkeley course's past exams (with solutions)
Week 7	Reinforcement Learning II, Probability [Reinforcement Learning II] [Probability]	Deep RL Bootcamp lectures Review of probability theory Common probability distribution Related research papers RL for POMDP Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates
Week 8	Bayes Nets: Representation, Independence [Bayes Nets I] [Bayes Nets II]	A Bayes Net tool that you can play with Review of probability theory Common probability distribution
Week 9	Bayes Nets: Inference, Sampling [Bayes Nets III] [Bayes Nets IV]	Related research papers Bayesian learning for safe high-speed navigation in unknown environments Dynamic Bayesian Network for semantic place classification in mobile robotics
Week 10	(Hidden) Markov Models, Particle Filters [Hidden Markov Models] [Particle Filters]	Markov Chain vs. HMM The readings on particle filters from Peter Stone's Fall 2015 graduate class on autonomous robots. Some are from the book "Probabilistic Robotics" by Thrun, Burgard, and Fox. The full list of resources from that class, including the following: Slides from the book: (ppt). Some videos from the textbook authors. Related research papers Vehicle localization using particle filter 3D Audio-Visual Speaker Tracking with an Adaptive Particle Filter Stochastic Simulation Algorithms for Dynamic Probabilistic Networks
Week 11	Review and schedule reserve	The Berkeley course's past exams (with solutions)
Week 12	Decision Networks, Naive Bayes [Decision Networks] [Naive Bayes]	Naive Bayes in Python and R An explanation of the connection between the number of bits required to encode a hypothesis and minimum description length (MDL) Clustering implementation Comparing Python Clustering Algorithms Clustering Vs. Classification on Keyword Research How Much Training Data is Required for Machine Learning? Related research papers Multi-face Detection System Design based on Naive Bayes Classifier Being Bayesian about Network Structure: A Bayesian Approach to Structure Discovery in Bayesian Networks
Week 13	Perceptrons, Clustering, Deep Learning [Perceptrons, Clustering] [Deep Learning]	From Perceptrons to Deep Networks Helpful Neural Net Notes: Backpropagation; Function approximation; CNN for Visual Recognition Goodfellow, Bengio, and Courville's Deep Learning book Open source deep learning software: PyTorch, TensorFlow Explanation on why ReLu is better Geoffrey Hinton talk: What is wrong with CNN Geoffrey Hinton's recent theory to replace deep learning UC Irvine Machine Learning (dataset) Repository Deep learning vs. kernel acoustic models for speech recognition Related research papers Deep Learning Generative Adversarial Networks Generating Sequences With Recurrent Neural Networks Designing Neural Network Architectures using Reinforcement Learning Attention Is All You Need
Week 14	Applications and schedule reserve
Week 15	Guest Lecture, Conclusion [Conclusions]	2022 AI Index Report and a summary on the report The killer drones video from Stuart Russell Why the Future Doesn't Need Us by Bill Joy - Wired, 2000 Why AI is Harder Than We Think The Essence of Soccer: Can Robots Play Too? Peter Stone, Michael Quinlan, and Todd Hester. A writing on the singularity: Ray Kurzweil's page. Jordan Pollack's GOLEM project: evolving physical robots. The Lifeboat Foundation is dedicated to assessing and protecting against threats to humanity. The Asilomar conference on recombinant DNA. Ben Kuipers' personal stance on accepting military research funding. 3 principles for creating safer AI Can we build AI without losing control over it?

Reference sequence

Lectures and Exercises

Additional Resources

Week 1