DOC PREVIEW
Berkeley COMPSCI 188 - Lecture 1 - Introduction

This preview shows page 1-2-3-4 out of 12 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

1CS 188: Artificial IntelligenceFall 2006Lecture 1: Introduction8/29/2006Dan Klein – UC BerkeleyMany slides over the course adapted fromeither Stuart Russell or Andrew Moore Administriviahttp://inst.cs.berkeley.edu/~cs1882 Course StaffCourse StaffDan GillickJohn DeNeroTamara BergDan KleinGSIsProfessorCourse Details Book: Russell & Norvig, AI: A Modern Approach, 2ndEd. Prerequisites: (CS 61A or B) and (Math 55 or CS 70)  There will be a lot of statistics and programming Work and Grading: 4 assignments divided into checkpoints Python, groups of 1-2, 5 late days Mid-term and final Participation Academic dishonesty policy3Announcements Important stuff: No section on 9/3 Python lab this Friday 1-5pm in 275 Soda Hall Get your account forms (in front after class) Mazeworld assignment on web very soon Questions?Today What is AI? Brief History of AI What can AI do? What is this course?4Sci-Fi AI?What is AI?Act rationallyAct like humansThink rationallyThink like humansThe science of making machines that:5Acting Like Humans? Turing (1950) ``Computing machinery and intelligence'' ``Can machines think?'' → ``Can machines behave intelligently?'' Operational test for intelligent behavior: the Imitation Game Predicted by 2000, a 30% chance of fooling a lay person for 5 minutes Anticipated all major arguments against AI in following 50 years Suggested major components of AI: knowledge, reasoning, languageunderstanding, learning Problem: Turing test is not reproducible or amenable to mathematical analysisThinking Like Humans? The Cognitive Science approach: 1960s ``cognitive revolution'': information-processing psychology replaced prevailing orthodoxy of behaviorism Scientific theories of internal activities of the brain What level of abstraction? “Knowledge'' or “circuits”? Cognitive science: Predicting and testing behavior of human subjects (top-down) Cognitive neuroscience: Direct identification from neurological data (bottom-up) Both approaches now distinct from AI Both share with AI the following characteristic: The available theories do not explain (or engender) anything resembling human-level general intelligence} Hence, all three fields share one principal direction!Images from Oxford fMRI center6Thinking Rationally? The “Laws of Thought” approach What does it mean to “think rationally”? Normative / prescriptive rather than descriptive Logicist tradition: Logic: notation and rules of derivation for thoughts Aristotle: what are correct arguments/thought processes? Direct line through mathematics, philosophy, to modern AI Problems: Not all intelligent behavior is mediated by logical deliberation What is the purpose of thinking? What thoughts should I (bother to) have? Logical systems tend to do the wrong thing in the presence of uncertaintyActing Rationally 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 Thinking can be in the service of rational action Entirely dependent on goals! Irrational ≠ insane, irrationality is sub-optimal action Rational ≠ successful Our focus here: rational agents Systems which make the best possible decisions given goals, evidence, and constraints In the real world, usually lots of uncertainty … and lots of complexity Usually, we’re just approximating rationality “Computational rationality” a better title for this course7Rational Agents An agent is an entity thatperceives and acts (moreexamples later) This course is about designingrational agents Abstractly, an agent is a functionfrom percept histories to actions: For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance Computational limitations make perfect rationality unachievable So we want the best program for given machine resourcesA (Short) History of AI 1940-1950: Early days 1943: McCulloch & Pitts: Boolean circuit model of brain 1950: Turing's ``Computing Machinery and Intelligence'‘ 1950—70: Excitement: Look, Ma, no hands! 1950s: Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: ``Artificial Intelligence'' adopted 1965: Robinson's complete algorithm for logical reasoning 1970—88: Knowledge-based approaches 1969—79: Early development of knowledge-based systems 1980—88: Expert systems industry booms 1988—93: Expert systems industry busts: “AI Winter” 1988—: Statistical approaches Resurgence of probability, focus on uncertainty General increase in technical depth Agents, agents, everywhere… “AI Spring”? 2000—: Where are we now?8What Can AI Do?Quiz: Which of the following can be done at present? Play a decent game of table tennis? Drive safely along a curving mountain road? Drive safely along Telegraph Avenue? Buy a week's worth of groceries on the web? Buy a week's worth of groceries at Berkeley Bowl? Discover and prove a new mathematical theorem? Converse successfully with another person for an hour? Perform a complex surgical operation? Unload a dishwasher and put everything away? Translate spoken English into spoken Swedish in real time? Write an intentionally funny story?Unintentionally Funny Stories One day Joe Bear was hungry. He asked his friend Irving Bird where some honey was. Irving told him there was a beehive in the oak tree. Joe walked to the oak tree. He ate the beehive. The End. Henry Squirrel was thirsty. He walked over to the river bank where his good friend Bill Bird was sitting. Henry slipped and fell in the river. Gravity drowned. The End. Once upon a time there was a dishonest fox and a vain crow. Oneday the crow was sitting in his tree, holding a piece of cheese in his mouth. He noticed that he was holding the piece of cheese. He became hungry, and swallowed the cheese. The fox walked over tothe crow. The End.[Shank, Tale-Spin System, 1984]9Natural Language Speech technologies Automatic speech recognition (ASR) Text-to-speech synthesis (TTS) Dialog systems Language processing technologies Machine translation:Aux


View Full Document

Berkeley COMPSCI 188 - Lecture 1 - Introduction

Documents in this Course
CSP

CSP

42 pages

Metrics

Metrics

4 pages

HMMs II

HMMs II

19 pages

NLP

NLP

23 pages

Midterm

Midterm

9 pages

Agents

Agents

8 pages

Lecture 4

Lecture 4

53 pages

CSPs

CSPs

16 pages

Midterm

Midterm

6 pages

MDPs

MDPs

20 pages

mdps

mdps

2 pages

Games II

Games II

18 pages

Load more
Download Lecture 1 - Introduction
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Lecture 1 - Introduction and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Lecture 1 - Introduction 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?