View
221
Download
3
Category
Tags:
Preview:
Citation preview
Introduction to Artificial Intelligence –Unit 1
What is AI?Course 240530
Dr. Avi RosenfeldBased on slides from
The Hebrew University of JerusalemSchool of Engineering and Computer Science
Instructor: Jeff Rosenschein
Week Breakdown
1. Introduction to A.I., Course Organization, Introduction to Search2. A*, Minimax, BFS, DFS, Heuristic search3. Local Search Constraint Satisfaction Problems, DSP and DCOP algorithms4. STRIPS and planning algorithms, Probability Theory and Bayesian Networks5. Web based A.I., information retrieval and recommender systems6. Neural Nets, Perceptrons and Machine Learning7. Knowledge Representation, Game Theory, Bounded Rationality and Fuzzy Logic8. NLP9. Agents and Multi-agent systems10. Robotics and Vision11. Multidisciplinary Topics And Applications12. Business Intelligence Applications13. Project #3 (B.I.)14. Review
2
Topics
What is A.I.?
Views of AI fall into four categories:
4
What is AI?
Thinking humanlyThinking humanly Thinking rationallyThinking rationally
Acting humanlyActing humanly Acting rationallyActing rationally
The AMAI textbook advocates “acting rationally”
The Brain vs. a ComputerComputerComputer Human BrainHuman Brain
Computational Computational UnitsUnits
1 CPU, 101 CPU, 1099 gatesgates
10101111 neurons neurons
Storage UnitsStorage Units 10101010 bits RAM bits RAM 10101111 neurons neurons
Cycle timeCycle time 1010-9-9 seconds seconds 1010-3-3 seconds seconds
BandwidthBandwidth 10101010 bits/sec bits/sec 10101414 bits/sec bits/sec
Memory Memory updates/secondupdates/second
101099 10101414
5
Why is it difficult to program computers to do what humans easily do? Recognize faces Understand human language
(Ironically, we can more successfully program computers to do what humans cannot easily do Play chess at world champion levels Carry out massive optimization problems)
Processing power? – doesn’t seem to be the real issue Software?
Scruffy vs. Neat debate
6
Artificial Intelligence
The Scruffy approach says, “Build systems that work, and principles will emerge.” E.g., the Wright Brothers building a
heavier-than-air flying machine The Neat approach says, “Explore
principles first, and having understood them, embody them in systems.” E.g., radar
7
Artificial Intelligence:Scruffy vs. Neat
Turing (1950) “Computing machinery and intelligence”:
“Can machines think?” “Can machines behave intelligently?”
Operational test for intelligent behavior: the Imitation Game
8
Acting humanly: Turing Test
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
9
Acting rationally: rational agent
Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997
Proved a mathematical conjecture (Robbins conjecture) unsolved for decades
No hands across America (driving autonomously 98% of the time from Pittsburgh to San Diego); DARPA Grand Challenges (and Google) show that cars can drive themselves inside and outside of cities
10
State of the art
During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people
NASA’s on-board autonomous planning program controlled the scheduling of operations for a spacecraft, and for the Mars Rover
Proverb solves crossword puzzles better than most humans
11
State of the Art
Introduction and Background: ½ week Search: 2 ½ weeks Knowledge Representation: 2 weeks Planning: 2 weeks Learning: 3 weeks Game Theory: 3 weeks Summation: 1 week
12
Topics We’ll Cover
IJCAI’07 Papers
1,365 papers submitted (authors from 45 different countries)
Accepted 471 papers (unusually high percentage that year, 34.4% accepted)
13
Number of accepted papers, by topic:
• Self-driving cars• Watson• Siri• Data-intensive applications that use
information analysis and learning to do things previously beyond machine capabilities
AI’s Recent High-Visibility Successes
14
DARPA’s Grand Challenge First Challenge: Driver-less vehicle go 130 miles
across desert This was not a simple task: it involved unclear roads,
tunnels, roads along cliffs, and the path was given to teams only hours before the race
2004: $1 million prize, utter failure 2005: $2 million prize
15
Google Cars, New York Times,IEEE Spectrum
16
How Google’s cars work:http://spectrum.ieee.org/automaton/robotics/artificial-intelligence/how-google-self-driving-car-works
Google Cars, New York Times
17
• Jeopardy is a quiz show, where answers are given, and 3 contestants compete to be the first to provide the question:– “Freud published this landmark study in 1899.”
• What is “The Interpretation of Dreams”?
• In 2011, Watson competed against Ken Jennings (who had the longest championship streak, 75 days), and Brad Rutter, the all-time biggest money winner on the show
• Final Score: Watson, $77,147;Jennings, $24,000, Rutter, $21,600
IBM’s Watson
18
• “The first person mentioned by name in ‘The Man in the Iron Mask’ is this hero of a previous book by the same author.”
• “Hemophilia is a hereditary condition in which this coagulates extremely slowly.”
• This director, better known as an actor, directed his wife Audrey
• “A long, tiresome speech delivered by a dessert topping.”
IBM’s Watson, Jeopardy Winner
19
20
Google’s News Page
Microsoft, Yahoo, and Google all take this very, very seriously
Peter Norvig, Google Director of Research Ron Brachman, built AT&T’s AI Research group,
now Vice President of Worldwide Research Operations at Yahoo
Eric Horvitz, head of Adaptive Systems & Interaction Group, Microsoft Research
AI Theory and AI Practice are looked to for solutions
21
AI Researchers Head Major Industry Research Labs
Ad Auctions “Google reported
revenues of $5.19 billion for the quarter ended March 31, 2008”
The vast majority of this is from those little ads on the right of the page
22
23
Recommendation SystemsCollaborative
FilteringPioneered by, among others, Konstan and Riedl, GroupLens
Commercial sites that use collaborative filtering include:AmazonBarnes and NobleDigg.comhalf.ebay.comiTunesMusicmatchNetflix (the Netflix Prize, grand prize of $1,000,000 for algorithm that beats Netflix's own by 10%)TiVo…
Go through large amounts of data Extract meaningful insight Local Example: Ronen Feldman, Business
School professor at Hebrew University (formerly Bar Ilan University), founded ClearForest (bought by Reuters)
24
Data Mining
Collaborative Filtering plusData Mining
“The search for a better recommendation continues with numerous companies selling algorithms that promise a retailer more of an edge. For instance, Barneys New York, the upscale clothing store chain, says it got at least a 10 percent increase in online revenue by using data mining software that finds links between certain online behavior and a greater propensity to buy. Using a system developed by Proclivity Systems, Barneys used data about where and when a customer visited its site and other demographic information to determine on whom it should focus its e-mail messages.” – New York Times, 19.5.08
25
26
Spam Filters
When all those emails from Barneys New York become oppressive…
27
Comparative Shoppers
Pioneered by, among others, Bruce Krulwich (BargainFinder), Oren Etzioni (MetaCrawler, NetBot [bought by Excite in 1997])
Comparison Shopping Plus Learning
FareCast (formerly Hamlet) tracks airline prices, advises whether to buy now or wait until later
Founded by Oren Etzioni, bought by Microsoft in April 2008
28
Integrate information in a more sophisticated way “What were the combined earnings from ad
auctions across Google, Yahoo, and Microsoft in 2007?”
Plan “How can I drive from San Francisco to Los
Angeles, in a way that reasonably maximizes the number of Starbucks stores I pass?”
29
What Can’t They Do (Yet)?
30
Translation
Speech Understanding
Nuance’s Dragon NaturallySpeaking and IBM’s ViaVoice
31
"FREE VOICE MAIL TRANSCRIPTIONS: From now on, you don’t have to listen to your messages in order; you don’t have to listen to them at all. In seconds, these recordings are converted into typed text. They show up as e-mail messages or text messages on your cellphone."
32
Google Voice, 11.3.09
iPhone Voice Control (pre-Siri)
33
Computational Biology Techniques from Computer Science in general,
and Artificial Intelligence in particular, are being used in the exploration of biological questions
AI researchers have played an important role in this (e.g., Daphne Koller, Nir Friedman)
34
Biology
Computer Games Realistic single-agent and
multi-agent activity in cooperative and competitive environments
What they call “AI” often isn’t But they are getting more
serious about it: Companies have started up
exploring Game AI Training programs (often military
training) for reacting to realistic situations
35
Other Games: Poker Active research and
competitions (machine vs. machine, machine vs. person) in Texas Hold-Em [University of Alberta, Carnegie-Mellon University]
Different domain than chess – imperfect information
CMU team is making use of game theoretic equilibrium concepts in their software
36
More Game Theory… Milind Tambe’s group at USC
studied optimal strategies for intrusion detection, “Playing Games for Security: An Efficient Exact Algorithm for Solving Bayesian Stackelberg Games”, AAMAS’08
Interesting theoretical work, focused on efficient algorithms
Deployed for last 18 months at LAX airport in Los Angeles to tell guards how to patrol
37
Operating Systems Programming Languages
SmallTalk Lisp
User Interface Design Advances in use of (not invention of) windows,
pointing devices, bitmapped graphics Web Services XML
38
Contributions to Other Computer Science Fields
• Who is responsible if a self-driving car is at fault in a crash?– The software developer?– The company that installed the software?– The driver that trusted the software?– Society?
A Moment on AI Ethics
39
The agent function maps from percept histories to actions:
[f: P* A] The agent program runs on the physical architecture
to produce f agent = architecture + program
40
Agents and environments
An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators
Human agent: eyes, ears, and other organs for sensors; hands, legs, mouth, and other body parts for actuators
Robotic agent: cameras and infrared range finders for sensors; various motors for actuators
41
Agents
Recommended