인공지능 (Artificial Intelligence)

• 강의실: 공학 3관 xxx호
• Textbooks
  • Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (Third edition), Prentice Hall, 2010 [book]
• Textbooks (additional)
  • D. L. Poole, A. K. Mackworth, Artificial Intelligence: Foundations of Computational Agents, (2nd edition), Cambridge University Press, 2017 [book]
  • I. Goodfellow, Y. Bengio, A. Courville, Deep learning, MIT Press, 2016 [book]
  • Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, MIT Press, 1998 [link] [2nd_edition]
  • D. Koller and N. Friedman, Probabilistic Graphical Models: Principles and Techniques, MIT Press, 2009 [book]
• References
  • TensorFlow [link]
  • Tensorflow Lecture at Stanford U. [link]
  • AI lecture at Brown Univ.
  • AI lecture at Berkeley Univ. [link]
  • AIML lecture at Princeton Univ. [link]
  • Deep RL lecture at Berkeley Univ. [link]
  • Deep RL Tutorial at ICML '17 [link]

• Lecture 1: Introduction [pdf]
• [Lecture at Brown U] Introduction [pdf]
• [Russell] Introduction [pdf]
• Lecture 2: Rational agents [pdf]
• Intelligent Agent [pdf]
• Lecture 3: Problem solving by search [pdf]
• [lecture at Brown U] [pdf]
• [Russell] Problem solving and search [pdf]
• [Russell] Problem solving and search [pdf]
• Lecture 4: Informed search [pdf]
• Beyond classical search [pdf]
• A* Parsing (by D. Klein and C. Manning) [pdf]
• [Lecture at Brown U]: Informed search [pdf]
• [Russell] Informed search [pdf], Local search [pdf]
• Lecture 5: Constraint satisfaction problems [pdf] [pdf]
• [Sandholm] Constraint satisfaction problems [pdf]
• [Russell] Constraint satisfaction problems [pdf]
• [Ref.] Cheeseman, P., Kanefsky, B., & Taylor, W. (1991). Where the really hard problems are. IJCAI '91 [pdf]
• Lecture 6: Adversarial search [pdf] [pdf]
• [Lecture at Brown U] Adversarial search [pdf]
• [Russell] Game playing [pdf], AlphaGo [pdf], MoGo [pdf]
• Lecture 7: Propositional logic [pdf]
• [Lecture at Princeton U] [pdf]
• [Lecture at Brown U] [pdf]
• [Russell] Logical agent [pdf]
• Lecture 8: Satisfiability and model construction [pdf] [pdf]
• Lecture 9: Predicate logic [pdf]
• SWI-Prolog [link], Sample [pdf]
• Prolog Tutorial [link] [pdf][pdf]
• [Lecture at Brown U] [pdf]
• [Russell] First order logic [pdf]
• Lecture 10: Knowledge_representation [pdf]
• Lecture 11: Modern knowledge base: Introduction [pdf], YAGO [pdf], KnowItAll
• YAGO: A core of semantic knowledge unifying WordNet and Wikipedia, WWW '07 [pdf][link]
• YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia, AI '13 [pdf]
• Knowledge Vault, KDD '14 [pdf]
• KnowItAll, WWW '04 [pdf]
• Lecture 12: Classical Planning [pdf]
• AAAI '17 tutorial: Planning and Robotics[pdf]
• ICAPS Competitions [link]
• [Ref] B. Bonet, H. Geffner, Planning as heuristic search, AI '01 [pdf]
• [Ref] J. Hoffmann, B. Nebel, The FF Planning Systems, JAIR '01 [pdf]
• [Ref] Action Planning: Computational Complexity [pdf]
• [Lecture at Brown U] [pdf]
• Lecture 13: Modern board game AI - Monte Carlo Tree Search [pdf] [pdf]
• Lecture 14: RL - Introduction [pdf]
• Lecture 15: RL - Markov Decision Process[pdf]
• Lecture 16: RL - Planning in Markov Decision Process [pdf]
• Lecture 17: RL - Monte Carlo learning [pdf]
• Lecture 18: RL - Temporal difference learning (Q-learning, SARSA)[pdf]
• Lecture 19: RL - Value function approximation [pdf]
• Lecture 20: RL - Deep Q learning [pdf]
• Lecture 21: RL - Policy gradient [pdf] [pdf]
• Lecture 22: RL - Summary [pdf]
• Lecture 23: Neural networks [pdf]
• Lecture 24: Probabilistic reasoning [pdf]
• Lecture 25: Probabilistic graphical model [pdf]
• [Ref] Koehn. Bayesian network [pdf]
• Lecture 26: Probabilistic reasoning over time [pdf]
• Lecture 27: Statistical learning [pdf]
• Lecture 28: AI: Philosophical foundations

• Assignment 1: [pdf]
• Assignment 2: [pdf]
• Assignment 3: [pdf]