Catalog

Artificial Intelligence

Electrical Engineering and Computer Science MIT CC BY-NC-SA 4.0 30 lectures

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.

Syllabus

  1. 1 Lecture 1: Introduction and Scope
  2. 2 Lecture 2: Reasoning: Goal Trees and Problem Solving
  3. 3 Lecture 3: Reasoning: Goal Trees and Rule-Based Expert Systems
  4. 4 Lecture 4: Search: Depth-First, Hill Climbing, Beam
  5. 5 Lecture 5: Search: Optimal, Branch and Bound, A*
  6. 6 Lecture 6: Search: Games, Minimax, and Alpha-Beta
  7. 7 Lecture 7: Constraints: Interpreting Line Drawings
  8. 8 Lecture 8: Constraints: Search, Domain Reduction
  9. 9 Lecture 9: Constraints: Visual Object Recognition
  10. 10 Lecture 10: Introduction to Learning, Nearest Neighbors
  11. 11 Lecture 11: Learning: Identification Trees, Disorder
  12. 12 Lecture 12A: Neural Nets
  13. 13 Lecture 12B: Deep Neural Nets
  14. 14 Lecture 13: Learning: Genetic Algorithms
  15. 15 Lecture 14: Learning: Sparse Spaces, Phonology
  16. 16 Lecture 15: Learning: Near Misses, Felicity Conditions
  17. 17 Lecture 16: Learning: Support Vector Machines
  18. 18 Lecture 17: Learning: Boosting
  19. 19 Lecture 18: Representations: Classes, Trajectories, Transitions
  20. 20 Lecture 19: Architectures: GPS, SOAR, Subsumption, Society of Mind
  21. 21 Lecture 21: Probabilistic Inference I
  22. 22 Lecture 22: Probabilistic Inference II
  23. 23 Lecture 23: Model Merging, Cross-Modal Coupling, Course Summary
  24. 24 Mega-Recitation 1: Rule-Based Systems
  25. 25 Mega-Recitation 2: Basic Search, Optimal Search
  26. 26 Mega-Recitation 3: Games, Minimax, Alpha-Beta
  27. 27 Mega-Recitation 4: Neural Nets
  28. 28 Mega-Recitation 5: Support Vector Machines
  29. 29 Mega-Recitation 6: Boosting
  30. 30 Mega-Recitation 7: Near Misses, Arch Learning

Course materials