DOC PREVIEW
CORNELL CS 472 - Foundations of Artificial Intelligence

This preview shows page 1 out of 4 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 4 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 4 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Foundations of Artificial IntelligenceCS472/CS473 — Fall 2005Slide CS472 – Introduction 1IntroductionWhere: Olin 155When: Mon, Wed, Fri 11:15–12:05Professor: Thorsten Joachims, Computer ScienceEmail: [email protected]: www.cs.cornell.edu/People/tjOffice Hours: 4153 Upson, Fr 1:30-2:30Course web site:www.cs.cornell.edu/courses/CS472/2005fa/Teaching Assistants: Filip Radlinski, Alexa Sharp,David Lin, Justin Dewitt.Office hours posted on-line.Slide CS472 – Introduction 2SyllabusProblem solvingprinciples of search, uninformed search, informed (heuristic)search, genetic algorithms, game playingLearninginductive learning, concept formation, decision tree learning,statistical approaches, neural networksKnowledge representation and reasoningknowledge bases and inference; constraint satisfaction;planning; theorem-proving; Bayesian networksNatural language understandingsyntactic processing, ambiguity resolution, text understandingSlide CS472 – Introduction 3General Information for CS472Text:Artificial Intelligence: A Modern ApproachRussell and Norvig, Prentice-Hall, Inc., second edition.Class Notes and Handouts:Available from course web site / CMSHomework: approx. 6 homework assignmentsExaminations: two prelims, one final exam.Prerequisites:programming (CS211 or CS312), basic math (CS280)Slide CS472 – Introduction 4Tentative Grading Policy (CS472)Assignments 45%Prelims 25%Final Exam 25%Participation/Interest 5%Late assignments drop 5% per each late day.Roughly: A=90-100; B=80-90; C=70-80; D=60-70; F= below 60Slide CS472 – Introduction 5Project (CS473)Goal :• Hands-on experience with AI methods• Ties into your research interestsFormat :• Self-defined project• Work in group of at least 3 students• Contains substantial programming componentSlide CS472 – Introduction 6Tentative Grading Policy (CS473)Preliminary Project Proposal 5%Project Proposal 10%Status Report 1 10%Status Report 2 10%Final Code (15%), Write-up (40%), and Demo (10%) 65%Late assignments drop 5% per each late day.Roughly: A=90-100; B=80-90; C=70-80; D=60-70; F= below 60Slide CS472 – Introduction 7Today’s LectureWhat is Artificial Intelligence (AI) anyway?— the components of intelligenceThe Current Frontier.— recent achievementsCurrent Challenges.— what makes AI problems hard?Slide CS472 – Introduction 8What is Intelligence?Intelligence:— “the capacity to learn and solve problems”(Webster dictionary)— the ability to think and act rationallyGoal in Artificial Intelligence:— build and understand intelligent systems/agents— synergy between• philosophy, psychology, and cognitive science• computer science and engineering• mathematics and physicsSlide CS472 – Introduction 9What’s involved in Intelligence?A) Ability to interact with the real world— to perceive, understand, and act— speech recognition, understanding, and synthesis— i mage understanding (computer vision)B) Reasoning and Planning— modelling the external world— p roblem solving, planning, and decision making— ability to deal with unexpected problems, uncertaintiesC) Learning and Adaptation— we are continuously learning and adaptingAlso: we want systems that adapt to us!— Major thrust of industry research.Slide CS472 – Introduction 10What is Artificial Intelligence?Rich and Knight: the study of how to make computers dothings which, at the moment, people do better.Handbook of AI: the part of computer science concernedwith designing intelligent computer systems, that is,systems that exhibit the characteristics we associate withintelligence in human behavior – understandinglanguage, learning, reasoning, solving problems, etc.Dean, Allen and Aloimonos: the design and study of thecomputer programs that behave intelligently.Russell and Norvig: the study of [rational] agents thatexist in an environment and perceive and act.Slide CS472 – Introduction 11Different ApproachesI Building exact models of human cognition— view from psychology and cognitive scienceII The logical thought approachemphasis on “correct” inferenceIII Building rational “agents”agent: something that perceives and actsemphasis on developing methods to match or exceedhuman performance [in certain domains]Example: Deep Blue.Our focus is on III (most recent progress).Slide CS472 – Introduction 12Goals in AIengineering goal To solve real-world problems. Buildsystems that exhibit intelligent behavior.scientific goal To understand what kind of computationalmechanisms are needed for modeling intelligent behavior.Slide CS472 – Introduction 13Turing Test• Interrogator asks questions of two “people” who are out ofsight and hearing. One is a person; the other is a machine.• 30 minutes to ask whatever he or she wants.• Task: to d etermine, only through the questions and answerstyped into a computer terminal, which is which.• If can’t reliably distinguish the human from the computer,then the computer is deemed intelligent.Artificial intelligence is the enterprise of constructing anartifact that can pass the Turing test.Slide CS472 – Introduction 14Objections to Turing Test?Newell and Simon [1976]• Turing test is as much a test of the judge as it is of themachine.• Promotes the development of artificial con-artists notartificial intelligence (Loebner competition).Slide CS472 – Introduction 15The Current FrontierInteresting time for AI•Deep Blue vs. Kasparov (May, ’97)–first match won against world-champion–“intelligent & creative” play–200 million board positions per secondKasparov: “I could feel — I could smell — anew kind of intelligence across the table.”... still understood 99.9% of Deep Blue’s moves.Intriguing issue: How does human cognition deal withthe combinatorics of chess?Slide CS472 – Introduction 16Different Algorithm, Similar BehaviorDrew McDermott (New York Times, May, 1997):Saying Deep Blue doesn’t really think about chess is like saying anairplane doesn’t really fly because it doesn’t flap its wings.ftp://ftp.cs.yale.edu/pub/mcdermott/papers/deepblue.txtThe brain— a neuron is the basic processing unit ( 1011)— many more synapses (1014) connect the neurons—cycletime:10−3seconds (1 millisecond)How complex can we make computers?—107or more transistors per CPU— supercomputer: hundreds of CPUs, 1010bits of RAM— cycle times: order of 10−9secondsSlide CS472 – Introduction 17Examples, cont.• First “creative” proof by computer


View Full Document

CORNELL CS 472 - Foundations of Artificial Intelligence

Download Foundations of Artificial Intelligence
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 Foundations of Artificial Intelligence 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 Foundations of Artificial Intelligence 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?