Patrick Winston
Artificial Intelligence — thirty lectures from MIT, Fall 2010.Artificial Intelligence. Thirty lectures from MIT’s Fall 2010 course: Introduction and Scope, Reasoning: Goal Trees and Problem Solving, Search: Depth-First, Hill Climbing, Beam and Search: Optimal, Branch and Bound, A*.
Artificial Intelligence · 30 lectures
Introduction and Scope
Reasoning: Goal Trees and Problem Solving
Reasoning: Goal Trees and Rule-Based Expert Systems
Search: Depth-First, Hill Climbing, Beam
Search: Optimal, Branch and Bound, A*
Search: Games, Minimax, and Alpha-Beta
Constraints: Interpreting Line Drawings
Constraints: Search, Domain Reduction
Constraints: Visual Object Recognition
Introduction to Learning, Nearest Neighbors
Learning: Identification Trees, Disorder
a: Neural Nets
b: Deep Neural Nets
Learning: Genetic Algorithms
Learning: Sparse Spaces, Phonology
Learning: Near Misses, Felicity Conditions
Learning: Support Vector Machines
Learning: Boosting
Representations: Classes, Trajectories, Transitions
Architectures: GPS, SOAR, Subsumption, Society of Mind
Probabilistic Inference I
Probabilistic Inference II
Model Merging, Cross-Modal Coupling, Course Summary
Mega-R1. Rule-Based Systems
Mega-R2. Basic Search, Optimal Search
Mega-R3. Games, Minimax, Alpha-Beta
Mega-R4. Neural Nets
Mega-R5. Support Vector Machines
Mega-R6. Boosting
Mega-R7. Near Misses, Arch Learning