230 likes | 347 Vues
This lecture introduces the foundations of Artificial Intelligence (AI) and the concept of intelligent agents as part of the CS482/682 course at the University of Nevada, Reno, taught by Kostas Bekris. Topics covered include the distinction between human-like and rational thinking, decision-making in deterministic and stochastic environments, and learning in unknown environments. The lecture further explores single-agent and multi-agent decision strategies, including dynamic programming, game theory, and machine learning techniques such as decision trees and neural networks.
E N D
Computer Science & Engineering, University of Nevada, Reno CS482/682Artificial Intelligence • Lecture 1: • The Foundations of AI • and Intelligent Agents 25 August 2009 Instructor: Kostas Bekris
What is AI? Humanly vs. Rationally Thinking vs. Acting
What is AI? Humanly vs. Rationally Thinking vs. Acting
What is AI? Humanly vs. Rationally Thinking vs. Acting
What is AI? Humanly vs. Rationally Thinking vs. Acting
What is AI? Humanly vs. Rationally Thinking vs. Acting
Structure of the Course • Part 1. • Decision-Making in Deterministic Environments • Single-agent: Dynamic programming and search, informed search and heuristics, randomized search, genetic algorithms, constraint satisfaction and path planning • Multi-agent: Adversarial search (mini-max and expecti-mini-max) • Part 2. • Decision-Making in Stochastic Environments • Single-agent: Bayesian networks, Hidden Markov Models, Kalman and Particle filters, Decision and Utility theory, Markov Decision Processes • Multi-agent: Introduction to Game Theory • Part 3. • Learning in Unknown Environments • Supervised learning: Decision trees, Support Vector Machines, Neural Networks • Unsupervised learning: Introduction to Reinforcement Learning
What are my personal interests? • Agents that must and do appropriately model and reason about the physical properties of their environment: • algorithmic generation of motion (motion planning) • state estimation problems given noisy sensors • and distributed message-passing coordination Robotics Physically-Grounded Agents Computer Games Human Assistants