1. Introduction to Artificial Intelligence Mitch Marcus CIS391 Fall, 2008

2. CIS 391 – Fall 2008 2 Welcome to CIS 391  Course home page: http://www.cis.upenn.edu/~cse391http://www.cis.upenn.edu/~cse391  Textbook: S. Russell and P. Norvig Artificial Intelligence: A Modern Approach Prentice Hall, 2003, Second Edition  Lecturer: Mitch Marcus, mitch@cis.upenn.edu, Levine 503mitch@cis.upenn.edu  TA: Ryan Gabbard, gabbard@seas.upenn.edu, Levine 554gabbard@seas.upenn.edu  TA: Qiuye (Sophie) Zhao, qiuye@seas.upenn.edu, Levine 571qiuye@seas.upenn.edu  Prerequisites: CSE 121, (CSE 260)  For Grading details, see Handout…

3. CIS 391 – Fall 2008 3 “Computers who will proud of us”

4. CIS 391 – Fall 2008 4 A REAL Accomplishment: DARPA Grand Challenge

5. CIS 391 – Fall 2008 5 A REAL Accomplishment: DARPA Urban Challenge

6. CIS 391 – Fall 2008 6 Some Real Accomplishments of AI  DARPA Grand Challenge – 123 miles through the desert  DARPA Urban Challenge – Autonomous Driving in Traffic!  Deep Space 1 – Remote Agent Experiment  Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997  Proved a mathematical conjecture (Robbins conjecture) unsolved for decades  Logistics Planning for 1991 Gulf War  Computer Algebra Systems  Credit Evaluation  Fraud Detection  Spam Filtering

7. CIS 391 – Fall 2008 7 What is AI? Views of AI fall into four categories: Thinking humanlyThinking rationally Acting humanlyActing rationally We will focus on "acting rationally" Thinking humanlyThinking rationally Acting humanlyActing rationally

8. CIS 391 – Fall 2008 8 Acting humanly: Turing Test  Turing (1950) "Computing machinery and intelligence": “Can machines think?”  “Can machines behave intelligently?”  Operational test for intelligent behavior: the Imitation Game  Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for 5 minutes  Anticipated most major arguments against AI  Suggested major components of AI: knowledge, reasoning, language understanding, learning Thinking humanlyThinking rationally Acting humanlyActing rationally

9. CIS 391 – Fall 2008 9 Thinking humanly: cognitive modeling  1960s "cognitive revolution": information-processing psychology  Requires scientific theories of internal activities of the brain  How to validate? Requires 1) Predicting and testing behavior of human subjects (top-down) or 2) Direct identification from neurological data (bottom-up)  Both approaches (roughly, Cognitive Science and Cognitive Neuroscience) are now distinct from AI Thinking humanlyThinking rationally Acting humanlyActing rationally

10. CIS 391 – Fall 2008 10 Thinking rationally: "laws of thought"  Aristotle: what are correct arguments/thought processes?  Several Greek schools developed various forms of logic: notation and rules of derivation for thoughts; may or may not have proceeded to the idea of mechanization  Direct line through mathematics and philosophy to modern AI  Problems: 1.Not all intelligent behavior is mediated by logical deliberation 2.What is the purpose of thinking? What thoughts should I have? 3.Ignores the hard problem of perception Thinking humanlyThinking rationally Acting humanlyActing rationally

11. CIS 391 – Fall 2008 11 Acting rationally: rational agents  Rational behavior: doing the right thing  The right thing: that which is expected to maximize goal achievement, given the available information  Doesn't necessarily involve thinking – e.g., blinking reflex – but thinking should be in the service of rational action Thinking humanlyThinking rationally Acting humanlyActing rationally

12. CIS 391 – Fall 2008 12 Rational agents  An agent is an entity that perceives and acts  This course is about effective programming techniques for designing rational agents  Abstractly, an agent is a function from percept histories to actions: [f: P*  A ]  For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance  Caveat: computational limitations make perfect rationality unachievable  design best program for given machine resources Thinking humanlyThinking rationally Acting humanlyActing rationally

13. CIS 391 – Fall 2008 13 Rational Agent skills can include: ReasoningSearchMachine Learning Representation of the World Symbols (Logic, Numbers) Vision Processing Planning Robotics Natural Language Understanding

14. CIS 391 – Fall 2008 14 Course Highlights 0. Introduction & Python Programming 1.Search Strategies, Constraint Satisfaction, Adversarial Games  Homework: Build a solver for any Sudoku problem  Final Project: Build a bot that competes against other game bots to play a simple board game (Kingdoms) 2.Knowledge Representation and Logic  Homework: Build an agent that plays Hunt the Wumpus using propositional logic theorem proving 3.Machine Learning: Perceptrons, Naïve Bayes, etc.  Homework: Build a spam filter using Naïve Bayes machine learning

15. CIS 391 – Fall 2008 15 More Detail – First Half Module 0: Introduction Intelligent Agents Python Programming (Week long introduction) Module 1: Search Strategies Uninformed & Informed Search Constraint Satisfaction (Sudoku Solver) Adversarial Search (Game Playing) Module 2: Knowledge Representation and Logic Logical Agents (Automated Wumpus adventurer) Topics in Knowledge Representation (Midterm more or less here)

16. CIS 391 – Fall 2008 16 More Detail – Second Half Module 3: Machine Learning and Natural Language Processing Introduction to Probability and Bayesian Networks Naive Bayes (Spam Filtering) Hidden Markov Models & Part of Speech Tagging Decision Trees Perceptrons and Support Vector Machines (Context Free Parsing for English)