introduction to ai russell and norvig: chapter 1 cmsc421 – fall 2006
Post on 22-Dec-2015
270 views
TRANSCRIPT
Introduction to AIIntroduction to AI
Russell and Norvig: Chapter 1 CMSC421 – Fall 2006
Meta-Intro
Personnel: Myself, two TAs: Galileo Namata and Vivek SehgalAnswers to some important questions: What are the prerequisites for this course? How can I do well in this course? What are the course logistics? How do we stay awake in the late
afternoon… ? What will we learn in this class?
What are the prerequisites?
Assume you know how to program. In addition, you should know: basic algorithms, data structures and
computational complexity i.e., searching graphs (DFS, BFS) lists, trees, graphs, etc. Difference between an O(n) and an O(2n)
algorithm basic logic
Truth table for x OR y, x AND y, x IMPLIES y basic probability
P(A v B) = P(A) + P(B) – P(A & B) P(A | B) = P(A & B) / P(B)
How do I do well in this course?
Attend classParticipate in classDo reading
Suggestion: 1) Set aside 20 minutes to skim chapter before lecture. 2) After lecture, go back and read the text in depth.
Start written assignments early Assignments are not designed to be done the night
before they are dueStart programming assignments EARLYDo practice problems to study for examsForm study groups. Working together (not copying) is highly encouraged**
** More on this in a few slides
What are the course logistics?
Web Page: http://www.cs.umd.edu/class/fall2006/cmsc4
21/
Mailing list: http://mailman.cs.umd.edu/mailman/listinfo/
cmsc421_2006
Forum: https://
forum.cs.umd.edu/forumdisplay.php?f=43
How do we stay awake?
and learn something, !Course Ettiquette:
Arrive to class on time; if you must leave during class, please try to limit the disruption/distraction
No cell phones, no side discussions No laptops during lectures Participate, Participate, Participate
ask questions – if you don’t understand the material, probably there is someone else who does not either!
some in class exercises Feedback:
please provide feedback there will be several opportunities, but also feel free to
just come talk to me!
Summary Meta-Intro
Answers to some important questions: What are the prerequisites for this
course? How can I do well in this course? What are the course logistics? How do we stay awake in the late
afternoon… ? What will we learn in this class?
What is AI?What is AI?
Class Exercise #0, part A: On the 3x5 card you’ve been given,
write down what your definition of AI You may also want to copy your
definition to your notes, because you’ll be turning the card in (anonymously, no worries!)
We will collect these definitions in 3 minutes!
Found on the Web …Found on the Web …
AI is the simulation of intelligent human processesAI is the reproduction of the methods or results of human reasoning or intuitionAI is the study of mental faculties through the use computational methodsUsing computational models to simulate intelligent behaviorMachines to emulate humans
Intelligent behavior
Humans
Computer
Why AI?Cognitive Science: As a way to understand how natural minds and mental phenomena work
e.g., visual perception, memory, learning, language, etc.
Philosophy: As a way to explore some basic and interesting (and important) philosophical questions
e.g., the mind body problem, what is consciousness, etc.
Engineering: To get machines to do a wider variety of useful things
e.g., understand spoken natural language, recognize individual people in visual scenes, find the best travel plan for your vacation, etc.
AI CharacterizationsAI Characterizations
Discipline that systematizes and automates intellectual tasks to create machines that:
Think like humans
Think rationally
Act like humans Act rationally
#1: Act Like Humans#1: Act Like Humans
Behaviorist approachNot interested in how you get results, just the similarity to what human resultsExemplified by the Turing Test (Alan Turing, 1950).
Turing TestTuring TestInterrogator interacts with a computer and a person via a teletype. Computer passes the Turing test if interrogator cannot determine which is which.Loebner contest: Modern version of Turing Test, held annually, with a $100,000 prize. http://www.loebner.net/Prizef/loebner-prize.html Participants include a set of humans and a set of
computers and a set of judges. Scoring: Rank from least human to most human. Highest median rank wins $2000. If better than a human, win $100,000. (Nobody yet…)
#2: Think Like Humans#2: Think Like Humans
How the computer performs functions does matterComparison of the traces of the reasoning stepsCognitive science testable theories of the workings of the human mind
•Exemplified by•General Problem Solver (Newell and Simon)•Neural networks•Reinforcement learning
But:• some early research conflated algorithm performance => like human (and vice-versa)• Do we want to duplicate human imperfections?
#3: Thinking rationally
Exemplified by "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 Direct line through mathematics and philosophy to modern AI
Problems: 1. Not easy to translate informal real world
problem into formal terms (problem formulation is difficult)
2. While may be able to solve the problem in principal (i.e. decidable), in practice, may not get the answer in a reasonable amount of time (computationally intractable)
#4: Acting Rationally
Rational behavior: do the right thingAlways make the best decision given what is available (knowledge, time, resources)Perfect knowledge, unlimited resources logical reasoning (#3)Imperfect knowledge, limited resources (limited) rationality
•Connection to economics, operational research, and control theory•But ignores role of consciousness, emotions, fear of dying on intelligence
AI CharacterizationsAI Characterizations
Discipline that systematizes and automates intellectual tasks to create machines that:
#2: Think like humans
#3: Think rationally
#1: Act like humans #4: Act rationally
What is AI?What is AI?Class Exercise #0, part B: Hopefully you have received the AI definition
from another student in the course. Break into groups of 4 people In your groups:
Start by giving a quick introduction: name, year, etc. On the additional blank card each group has been
given, write each person in the groups name and email
Each person has a card; read the card to the group, and the group should decide the category:
#2: Think like humans #3: Think rationally
#1: Act like humans #4: Act rationally
Bits of HistoryBits of History1956: The name “Artificial Intelligence” was coined by John McCarthy. (Would “computational rationality” have been better?)Early period (50’s to late 60’s): Basic principles and generality General problem solving Theorem proving Games Formal calculus
Bits of HistoryBits of History1969-1971: Shakey the robot (Fikes, Hart, Nilsson) Logic-based planning (STRIPS)Motion planning (visibility graph)Inductive learning (PLANEX)Computer vision
Bits of HistoryBits of History
Knowledge-is-Power period (late 60’s to mid 80’s): Focus on narrow tasks require
expertise Encoding of expertise in rule form:
If: the car has off-highway tires and4-wheel drive andhigh ground clearance
Then: the car can traverse difficult terrain (0.8) Knowledge engineering 5th generation computer project CYC system (Lenat)
Bits of HistoryBits of History
AI becomes an industry (80’s – present): Expert systems: Digital Equipment,
Teknowledge, Intellicorp, Du Pont, oil industry, …
Lisp machines: LMI, Symbolics, … Constraint programming: ILOG Robotics: Machine Intelligence
Corporation, Adept, GMF (Fanuc), ABB, … Speech understanding Information Retrieval – Google, …
Predictions and Reality … Predictions and Reality … (1/3)(1/3)
In the 60’s, a famous AI professor from MIT said: “At the end of the summer, we will have developed an electronic eye”As of 2002, there is still no general computer vision system capable of understanding complex dynamic scenesBut computer systems routinely perform road traffic monitoring, facial recognition, some medical image analysis, part inspection, etc…
Predictions and Reality … Predictions and Reality … (2/3)(2/3)
In 1958, Herbert Simon (CMU) predicted that within 10 years a computer would be Chess championThis prediction became true in 1998Today, computers have won over world champions in several games, including Checkers, Othello, and Chess, but still do not do well in Go
Predictions and Reality … Predictions and Reality … (3/3)(3/3)
In the 70’s, many believed that computer-controlled robots would soon be everywhere from manufacturing plants to homeToday, some industries (automobile, electronics) are highly robotized, but home robots are still a thing of the futureBut robots have rolled on Mars, others are performing brain and heart surgery, and humanoid robots are operational and available for rent (see: http://world.honda.com/news/2001/c011112.html)
State of the Art
Drive safely along a curving mountain roadDrive safely along US 1 Buy a week’s worth of groceries on the webBuy a week’s worth of groceries at your local Giant Play a decent game of bridgeWrite an intentionally funny storyGive competent legal advice in a specialized area of lawTranslate spoken English into spoken Swedish in real timeConverse successfully with another person for an hourPlay a decent game of ping-pongUnload any dishwasher and put everything awayExplore the Martian landscapeExplore downtown Washington
Why is AI Hard?
Simple syntactic manipulation is not enough
•Machine Translation•Big project in 1957 following Sputnik launch•Translation of Russian documents
•‘The spirit is willing but the flesh is weak’•‘The vodka is strong but the meat is rotten’
ElizaELIZA: A program that simulated a psychotherapist interacting with a patient Coded at MIT during 1964-1966 by Joel Weizenbaum.First script was DOCTOR.
The script was a simple collection of syntactic patterns not unlike regular expressions
Each pattern had an associated reply which might include bits of the input (after simple transformations (my your)
Weizenbaum was shocked at reactions: Psychiatrists thought it had potential. People unequivocally anthropomorphized. Many thought it solved the NL problem.
• Try typing Meta-x doctor in Emacs.
• Recent Loebner Prize winner, http://www.alicebot.org/
Colby’s PARRYKenneth Colby modeled a paranoid using the same techniques circa 1968.PARRY has basic emotions. If it gets angry, its replies become more hostile. In a Turing test, expert psychiatrists were unable to distinguish PARRY’s ramblings from those of real paranoids.
H: Good afternoon. My name is Doctor Jones.
P: Pleased to meet you. H: How are you? P: All right I guess. H: Could you tell me your name? P: Pat Smith. H: I though you might have some
problems. P: I've been upset lately. H: By what? P: People get on my nerves
sometimes. H: Tell me more. P: Do you know anything about
bookies? ...
H: Good afternoon. My name is Doctor Jones.
P: Pleased to meet you. H: How are you? P: All right I guess. H: Could you tell me your name? P: Pat Smith. H: I though you might have some
problems. P: I've been upset lately. H: By what? P: People get on my nerves
sometimes. H: Tell me more. P: Do you know anything about
bookies? ...
Parry meets Eliza…
P: I don't understand your motives. E: Why don't you understand my
motives? P: Shouldn't I be? E: Why do you say that just now? P: That's just the way it is. E: Suppose that's the way it were not. P: So? E: I am not sure I understand you fully. P: You harp on the same questions too
much. E: What does that similarity suggest to
you? P: I don't get you. E: Do you wish that you did get I?
P: I don't understand your motives. E: Why don't you understand my
motives? P: Shouldn't I be? E: Why do you say that just now? P: That's just the way it is. E: Suppose that's the way it were not. P: So? E: I am not sure I understand you fully. P: You harp on the same questions too
much. E: What does that similarity suggest to
you? P: I don't get you. E: Do you wish that you did get I?
Why is AI Hard?
Computational intractability
•AI goal defined before notion of NP-completeness
•people thought to solve larger problems we simply need larger/faster computers•didn’t understand the notion of exponential growth
ALL of the algorithms we will study will be computational intractable (NP-complete as best) in the WORST case …
How does the fact that we are dealing with the REAL WORLD make solving these computationally challenging problems feasible IN PRACTICE?
CMSC 421CMSC 421
We will focus on the rational agents (“engineering”) paradigmMake computers act more intelligentlyThree major components: representation reasoning learning
Course overview
Introduction and Agents (chapters 1,2)Search (chapters 3,4,5,6)Logic (chapters 7,8,9)Planning (chapters 11,12)Uncertainty (chapters 13,14,15,16,17)Learning (chapters 18,20,21)
Learning Goals for Class
You will learn a bunch of tools that are useful for building useful, adaptive software… to solve fun and challenging problemsThese tools will be useful for you whether you go into AI research (basics that anyone should know) or any other discipline (oh, hey, that looks like the planning problems we studied way back in cmsc421)Help you separate hype from what’s easily achievable using existing tools (and avoid reinventing them!)