15-381: AI Introduction Instructors: Manuela Veloso and Luis von Ahn TAs: Sue Ann Hong, Gabriel Levi, Mary McGlohon, and Abe Othman http://www.cs.cmu.edu/afs/andrew/course/15/381-f09/www/ Carnegie Mellon15-381 AI Fall 2009 Grading 6 Problem sets - 50% Midterm - 20% Final - 30% Problem sets can be done in groups of up to 2 people – no need to have the same group for all homeworks. 8 “mercy” days (no penalty) for late homeworks, cannot use more than 2 mercy days in a single homework. No credit for late homeworks with no mercy days.15-381 AI Fall 2009 Resources Lectures Presentation and discussion in class Lecture slides annotated and enriched by TAs with examples and further details Instructors – office hours by appointment TAs – office hours will be announced15-381 AI Fall 2009 What is Artificial Intelligence? What is “intelligence” ?!Can we emulate intelligent behavior in machines ?!How far can we take it ?!15-381 AI Fall 2009 Intelligent Systems Three key steps (Craik, 1943): 1. the stimulus must be translated into an internal representation 2. the representation is manipulated by cognitive processes to derive new internal representations 3. internal representations are translated into action perception! cognition! action!15-381 AI Fall 2009 Views of AI Think like humans Cognitive Science Think rationally Formalize inference into laws of thought Act rationally Act according to laws Act like humans Turing test15-381 AI Fall 2009 Allen Newell d.1992 Wean Hall 5409 Carnegie Mellon University early 90s15-381 AI Fall 2009 Artificial Intelligence Computer Science: “The study of computers and the phenomena that surround them.” Alan Perlis, Allen Newell, Herb Simon Ambitious scientific pursuits: What is the nature of human intelligence? How does the brain work? How to solve problems effectively? How do humans and machines learn? How do we create intelligent creatures?15-381 AI Fall 2009 The Dartmouth Conference “We propose that a two-month, ten-man study of artificial intelligence be carried out during the summer of 1956 at Dartmouth College in Hanover, NH. The study is to proceed on the basis of the conjecture that every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it.”15-381 AI Fall 2009 The Proponents John McCarthy, assistant professor of mathematics at Dartmouth (Stanford) Marvin Minsky, Harvard junior fellow in mathematics and neurology (MIT) Nathaniel Rochester, manager of information research at IBM, NY (?) Claude Shannon, information theory, mathematician at Bell Labs (2001)15-381 AI Fall 2009 The Invited Trenchard More, IBM Arthur Samuel, IBM Oliver Selfridge, Lincoln Labs, MIT Ray Solomoff, MIT And “two vaguely known persons from RAND and Carnegie Tech… a significant afterthought.” (Pamela McCorduck, “Machines Who Think”, page 94)15-381 AI Fall 2009 Herbert A. Simon and Allen Newell15-381 AI Fall 2009 Problem Solving Allen Newell and Herb Simon – 1950s Given: an initial state a set of actions a goal statement Find a plan, a sequence of actions that transform the initial state into a state where the goal is satisfied15-381 AI Fall 2009 Search Find a sequence of states from current state to state that satisfies goal statement b a d p q h e c f r START GOAL15-381 AI Fall 2009 Schedule M Aug 24 – Introduction W Aug 26 – Uninformed search methods M Aug 31 – Informed search W Sep 2 – Stochastic search - HMW1 out M Sep 7 – No class, Labor’s Day W Sep 9 – More search M Sep 14 – Constraint satisfaction problems W Sep 16 - CSPs - HMW1 due, HMW2 out15-381 AI Fall 2009 Problem Solving Components Given the actions available in a task domain. Given a problem specified as: an initial state of the world, a set of goals to be achieved. Action Model, State, Goals15-381 AI Fall 2009 Actions, States, Goals15-381 AI Fall 2009 Representation All AI problems require some form of representation. • chess board!• maze!• text!• object!• room!• sound!• visual scene!A major part AI is representing the problem space so as to allow efficient search for the best solution(s).!15-381 AI Fall 2009 Intelligent Agents Sensing: vision, hearing, touch, smell, taste, … Cognition: think, reason, plan, learn, … Action: motion, speak, manipulation, … Interaction with other agents: negotiation, strategic behavior, speculation, …15-381 AI Fall 200915-381 AI Fall 2009 Perception – Sensors to State Sensors – “signal” (data) collectors from the physical world: Vision, sound, touch, sonar, laser, infrared, GPS, temperature,…. Signal-to-symbol challenge: Recognize the state of the environment …wall at 2m… door on the left… green light… person in front… personX entering the room… ball at 1m and 30o East…15-381 AI Fall 2009 Reasoning with uncertain information Most facts are not concrete and are not known with certainty. • inferences!• What disease?!• What causes?!• facts!• observations!• “fever”!• “aches”!• platelet count=N!Probabilistic inference: !How do we give the proper weight to each observation?!What is ideal?!15-381 AI Fall 2009 Reasoning with Uncertainty Reason (infer, make decisions, etc.) based on uncertain models, observations, knowledge Probability(Flu|TravelSubway) Bayes Nets15-381 AI Fall 2009 Schedule M Sep 21 – Deterministic reasoning, planning W Sep 23 – Uncertainty, robot motion planning M Sep 28 – Probability W Sep 30 – Bayesian networks - HMW2 due, HMW3 out M Oct 5 – Probabilistic reasoning W Oct 7 – Uncertainty HWM3 due, HMW4 out M Oct 12 – Review W Oct 14 – MIDTERM15-381 AI Fall 2009 Learning Automatically generate strategies to classify or predict from training examples Training data: good/bad mpg for example cars Mpg good/bad Predict mpg on new data15-381 AI Fall 2009 Learning Automatically generate strategies to
View Full Document