Loading…

MIT OpenCourseWare

Artificial Intelligence

This course introduces students to the basic knowledge representation, problem solving, and learning methods of artificial intelligence. Upon completion of 6.034, students should be able to develop intelligent systems by assembling solutions to concrete computational problems; understand the role of knowledge representation, problem solving, and learning in intelligent-system engineering; and appreciate the role of problem solving, vision, and language in understanding human intelligence from a computational perspective. (from ocw.mit.edu )

Instructor

Professor Patrick Henry Winston.

Computer science

2014

Lecture 01 - Introduction and Scope

Lecture 02 - Reasoning: Goal Trees and Problem Solving

Lecture 03 - Reasoning: Goal Trees and Rule-Based Expert Systems

Lecture 04 - Search: Depth-First, Hill Climbing, Beam

Lecture 05 - Search: Optimal, Branch and Bound, A*

Lecture 06 - Search: Games, Minimax, and Alpha-Beta

Lecture 07 - Constraints: Interpreting Line Drawings

Lecture 08 - Constraints: Search, Domain Reduction

Lecture 09 - Constraints: Visual Object Recognition

Lecture 10 - Introduction to Learning, Nearest Neighbors

Lecture 11 - Learning: Identification Trees, Disorder

Lecture 12 - Learning: Neural Nets, Back Propagation

Lecture 13 - Learning: Genetic Algorithms

Lecture 14 - Learning: Sparse Spaces, Phonology

Lecture 15 - Learning: Near Misses, Felicity Conditions

Lecture 16 - Learning: Support Vector Machines

Lecture 17 - Learning: Boosting

Lecture 18 - Representations: Classes, Trajectories, Transitions

Lecture 19 - Architectures: GPS, SOAR, Subsumption, Society of Mind

Lecture 21 - Probabilistic Inference I

Lecture 22 - Probabilistic Inference II

Lecture 23 - Model Merging, Cross-Modal Coupling, Course Summary