AI / ML Notes

Artificial Intelligence: A Modern Approach — Russell & Norvig, 4th edition

Chapter 1
1.1 The 4 Definitions of AI 2.2 Rational Agent Standard Model Value Alignment 3.3 Foundations Philosophy and Mathematics 4.4 Foundations Economics Neuroscience Psychology Linguistics 5.5 History Inception 1943 1956 6.6 History Early Enthusiasm 1952 1969 7.7 History Dose of Reality 1966 1973 8.8 History Expert Systems 1969 1986 9.9 History Neural Networks Probabilistic ML BigData DeepLearning 10.10 State of the Art 11.11 Risks and Benefits of AI
Chapter 2
1.1 Agents and Environments 2.2 Rationality and Performance Measures 3.3 Task Environments PEAS 4.4 Properties of Task Environments 5.5 The Four Agent Architectures 6.6 Learning Agents
Chapter 3
1.1 Problem Solving Agents and Search Formulation 2.2 Example Problems 3.3 Search Framework and Data Structures 4.4 Uninformed Search Strategies 5.5 Informed Heuristic Search and Astar 6.6 Memory Bounded Search 7.7 Heuristic Functions
Chapter 4
1.1 Beyond Classical Search Overview 2.2 Local Search Hill Climbing 3.3 Simulated Annealing 4.4 Population Based Methods 5.5 Local Search Continuous Spaces 6.6 Nondeterministic Actions AND OR Trees 7.7 Partial Observability Belief States 8.8 Online Search Agents
Chapter 5
1.1 Games and Adversarial Search 2.2 Minimax Algorithm 3.3 Alpha Beta Pruning 4.4 Heuristic Evaluation Functions 5.5 Monte Carlo Tree Search 6.6 Stochastic Games Expectiminimax 7.7 Partially Observable Games
Chapter 6
1.1 CSP Formulation and Examples 2.2 Constraint Propagation and Inference 3.3 Backtracking Search for CSPs 4.4 Local Search for CSPs 5.5 Problem Structure and Decomposition
Chapter 7
1.1 Knowledge Based Agents 2.2 Wumpus World 3.3 Logic Fundamentals Syntax Semantics Entailment 4.4 Propositional Logic 5.5 Logical Equivalences Validity Satisfiability 6.6 Inference and Proof Resolution 7.7 Horn Clauses Forward Backward Chaining 8.8 DPLL and WalkSAT
Chapter 8
1.1 First Order Logic Overview 2.2 FOL Syntax and Semantics 3.3 Using FOL Knowledge Engineering
Chapter 9
1.1 Inference in FOL Overview 2.2 Unification and Generalized Modus Ponens 3.3 Forward Backward Chaining FOL 4.4 Resolution in FOL
Chapter 10
1.1 Knowledge Representation Overview 2.2 Events Time and Situation Calculus 3.3 Default Reasoning and Ontologies
Chapter 11
1.1 Classical Planning and PDDL 2.2 Planning Algorithms and Heuristics 3.3 Planning Under Uncertainty
Chapter 12
1.1 Probability Basics
Chapter 13
1.1 Bayesian Networks 2.2 Exact Inference in BNs 3.3 Approximate Inference Sampling
Chapter 14
1.1 Temporal Models and Filtering 2.2 Kalman Filters and DBNs
Chapter 15
1.1 Probabilistic Programming
Chapter 16
1.1 Utility Theory and Decision Networks
Chapter 17
1.1 MDPs and Value Iteration 2.2 POMDPs and Bandit Problems
Chapter 18
1.1 Multiagent Decision Making
Chapter 19
1.1 Learning from Examples
Chapter 20
1.1 Learning Probabilistic Models
Chapter 21
1.1 Deep Learning
Chapter 22
1.1 Reinforcement Learning Fundamentals 2.2 Advanced RL and Applications
Chapter 23
1.1 Natural Language Processing
Chapter 24
1.1 Deep Learning for NLP
Chapter 25
1.1 Computer Vision
Chapter 26
1.1 Robotics
Chapter 27
1.1 Philosophy Ethics Safety of AI
Chapter 28
1.1 The Future of AI