Lecture 1: Introduction to Artificial Intelligence
Lecture 2: Uninformed Search
- BFS
- Uniform Cost Search
- DFS
- Depth-limited search
- Iterative deepening search
Lecture 3: Informed Search
- Greedy best-first search
- A* search
Lecture 4: Constraint Satisfaction
- Constraint Satisfaction Problem
- Backtracking Search
Lecture 5: Uncertainty
- Conditional Probability
- Bayes' Rule
- Probabilistic Inference
Lecture 6: Bayesian Networks
- Bayesian Networks
- Causal Intuitions
- Testing Independence
- D-separation
- Relevance: A Sound Approximation
Lecture 7: Bayesian Networks (continuation of the last lecture)
Lecture 8: Causal Inference
- Causal Bayesian Network
- Inference with Do Operator
- Counterfactual Analysis
Lecture 9: Probabilistic Reasoning over Time
- Stochastic Process
- Stationary process
- Markov assumption
- K-order Markov Process
- Hidden Markov Model
Lecture 10: Decision Tree Learning
- Choosing attribute tests
- Overfitting
- Cross-Validation
Lecture 11: Statistical Learning
- Bayesian Learning
- Maximum a posteriori (MAP)
- Maximum Likelihood (ML)
Lecture 12: Case Studies
Lecture 13: Neural Networks
- Perceptron
- Sequential Gradient Descent
Lecture 14: Deep Neural Networks
- Expressiveness
- Vanishing Gradients
- Rectified Linear Units
- Overfitting
Lecture 15: Decision Networks
- Preferences
- Decision Networks
Lecture 16: Markov Decision Processes
- Policy Optimization
- Value iteration
- Policy iteration
Lecture 17: Reinforcement Learning
- Model Free Evaluation
- Monte Carlo evaluation
- Temporal difference (TD) Evaluation
- Exploration vs Exploitation
Lecture 18: Deep Reinforcement Learning
- Function to be Approximated
- Mitigating divergence
- Experience Replay
- Target Network
Lecture 19: Model-based Reinforcement Learning
- Model-based RL (with Value Iteration)
- Model-based RL (with Q-learning)
Lecture 20: Multi-armed Bandits
Lecture 21: Game Theory
Lecture 22: Game Theory II
Lecture 23: Multi-agent RL