Introduction to Course DCP 1172

Download Report

Transcript Introduction to Course DCP 1172

DCP 1172
Introduction to Artificial Intelligence
Lecture 1
Chang-Sheng Chen
Today: 9/14
• Administrative stuff
• What is AI? Why study AI ?
• Overview of course topics
DCP 1172, Lecture 1
Administrative Stuff
•
•
•
•
•
•
Under-graduate course
Web page/Class mailing list
Reasonable preparation
Requirements
Computing Facility
Programming
DCP 1172, Lecture 1
DCP 1172: Introduction to Artificial Intelligence
• Instructor: Dr. Chang-Sheng Chen, [email protected]
• Lectures: Tue 15:40-16:30, Fri 10:10-12:00, EC-016
• Office hours: Thu 10:30 – 11:30 pm
• Room 328, Computer & Network Center and by appointment
• Course web page:
•
•
•
•
http://www.cc.nctu.edu.tw/~cschen/courses/2004/dcp1172.html
Up to date information
Lecture notes
Relevant dates, links, etc.
DCP 1172, Lecture 1
DCP 1172 : Introduction to Artificial Intelligence
• Course overview:
• foundations of symbolic intelligent systems. agents, search,
problem solving, logic, representation, reasoning, symbolic
programming, and robotics, etc.
• Prerequisites:
• Basic algorithm and data structure analysis
• Ability to program
• Some knowledge of Prolog/Lisp for some programming
assignments.
• Some exposure to logic
• Exposure to basic concepts in probability
• Familiarity with linguistics, psychology, and philosophy
DCP 1172, Lecture 1
DCP 1172 : Introduction to Artificial Intelligence
Requirements: READ the book!
• [AIMA] Artificial Intelligence: A Modern Approach
Russell and Norvig, 2nd Edition, Prentice-Hall 2003
Grading:
•
•
•
•
30% for mandatory homework assignments
15% for term project
25% for midterm
30% for final
DCP 1172, Lecture 1
Important things about this CLASS
Homework Late Policy
• Assignments are due in class, at the beginning of class, on the assigned due
date.
• That is unless you’ve made some arrangement with me ahead of time.
Programming
• The programming for this class will be done using
LISP/Prolog.
• Free versions are available for UNIX, Windows.
Forbidden Things
• Please don’t cheat, copy, plagiarize (剽竊/盜用) or otherwise make my life
and yours unpleasant.
DCP 1172, Lecture 1
Computing Facilities/Programming
• (I suppose) Most of the programming assignments
could be done using your own PC.
• However, if in need, we could installed another
Unix workstation (e.g., using FreeBSD) and you
could do your programming jobs there.
• The programming for this class will be done using
LISP and/or Prolog.
• Free versions are available for UNIX, Windows.
• GNU Prolog, etc.
• GNU Common Lisp, etc.
DCP 1172, Lecture 1
Course Topics
•
•
•
•
•
•
Agents
State space search
Knowledge representation
Uncertain reasoning
Machine learning
Modern AI Applications
•
•
•
•
•
Rule-based expert system
Fuzzy expert system
Artificial Neural Network
Evolutionary Computation
Hybrid Intelligent System
DCP 1172, Lecture 1
A Framework : What is AI?
The exciting new effort to
make computers thinks …
machine with minds, in the full
and literal sense”
(Haugeland 1985)
“The study of mental faculties
through the use of computational
models”
(Charniak et al. 1985)
“The art of creating machines
that perform functions that
require intelligence when
performed by people”
(Kurzweil, 1990)
A field of study that seeks to
explain and emulate intelligent
behavior in terms of
computational processes”
(Schalkol, 1990)
Systems that think like humans
Systems that think rationally
Systems that act like humans
Systems that act rationally
DCP 1172, Lecture 1
Our Framework
Getting computers to do the right thing based on
their circumstances and what they know.
• No presuppositions about how they should be designed to do
the right thing
• I.e. not limited to how people do it
• Evaluation is based on performance, not on how the task is
performed
DCP 1172, Lecture 1
Acting Humanly: The Turing Test
• Alan Turing's 1950 article Computing Machinery and
Intelligence discussed conditions for considering a machine to
be intelligent
• “Can machines think?”  “Can machines behave
intelligently?”
• The Turing test (The Imitation Game): Operational
definition of intelligence.
DCP 1172, Lecture 1
Acting Humanly: The Turing Test
• Computer needs to possess: Natural language processing,
Knowledge representation, Automated reasoning, and Machine
learning
• Are there any problems/limitations to the Turing
Test?
DCP 1172, Lecture 1
Why study AI?
Search engines
Science
Medicine/
Diagnosis
Labor
Appliances
DCP 1172, Lecture 1
What else?
Honda Humanoid Robot
Walk
Turn
http://world.honda.com/robot/
DCP 1172, Lecture 1
Stairs
Sony AIBO
http://www.aibo.com
DCP 1172, Lecture 1
Natural Language Question Answering
http://aimovie.warnerbros.com
http://www.ai.mit.edu/projects/infolab/
DCP 1172, Lecture 1
Robot Teams
USC robotics Lab
DCP 1172, Lecture 1
Applied Areas of AI
• Game playing
• Speech and language processing
• Expert reasoning
• Planning and scheduling
• Vision
• Robotics
…
DCP 1172, Lecture 1
What tasks require AI?
• “AI is the science and engineering of making intelligent
machines which can perform tasks that require intelligence
when performed by humans …”
• What tasks require AI?
DCP 1172, Lecture 1
What tasks require AI?
• Tasks that require AI:
• Solving a differential equation
• Brain surgery
• Inventing stuff
• Playing Jeopardy
• Playing Wheel of Fortune
• What about walking?
• What about grabbing stuff?
• What about pulling your hand away from fire?
• What about watching TV?
• What about day dreaming?
DCP 1172, Lecture 1
The Architectural Components of AI Systems
•
•
•
•
•
State-space search
Knowledge representation
Logical reasoning
Reasoning under uncertainty
Learning
DCP 1172, Lecture 1
Outlook
• AI is a very exciting area right now.
• This course will teach you the foundations.
DCP 1172, Lecture 1
Course Overview
General Introduction
•
01-Introduction. [AIMA Ch 1] Course Schedule. Homeworks, exams and grading.
Course material, TAs and office hours. Why study AI? What is AI? The Turing test.
Rationality. Branches of AI. Research disciplines connected to and at the
foundation of AI. Brief history of AI. Challenges for the future. Overview of class
syllabus.
•
02-Intelligent Agents. [AIMA Ch 2] What is
an intelligent agent? Examples. Doing the right
thing (rational action). Performance measure.
Autonomy. Environment and agent design.
Structure of agents. Agent types. Reflex agents.
Reactive agents. Reflex agents with state.
Goal-based agents. Utility-based agents. Mobile
agents. Information agents.
effectors
sensors
DCP 1172, Lecture 1
Agent
Course Overview (cont.)
How can we solve complex problems?
•
03/04-Problem solving and search. [AIMA Ch 3]
Example: measuring problem. Types of problems. More
example problems. Basic idea behind search algorithms.
Complexity. Combinatorial explosion and NP
completeness. Polynomial hierarchy.
•
05-Uninformed search. [AIMA Ch 3] Depth-first.
Breadth-first. Uniform-cost. Depth-limited. Iterative
deepening. Examples. Properties.
•
06/07-Informed search. [AIMA Ch 4] Best-first. A*
search. Heuristics. Hill climbing. Problem of local
extrema. Simulated annealing.
DCP 1172, Lecture 1
3l
5l
9l
Using these 3 buckets,
measure 7 liters of water.
Traveling salesperson problem
Course Overview (cont.)
Practical applications of search.
• 08/09-Game playing. [AIMA Ch 5] The minimax algorithm. Resource
limitations. Aplha-beta pruning. Elements of
chance and nondeterministic games.
tic-tac-toe
DCP 1172, Lecture 1
Course Overview (cont.)
Towards intelligent agents
• 10-Agents that reason logically 1.
[AIMA Ch 6] Knowledge-based
agents. Logic and representation.
Propositional (boolean) logic.
• 11-Agents that reason logically 2.
[AIMA Ch 6] Inference in
propositional logic. Syntax.
Semantics. Examples.
wumpus world
DCP 1172, Lecture 1
Course Overview (cont.)
Building knowledge-based agents: 1st Order Logic
• 12-First-order logic 1. [AIMA Ch 7] Syntax. Semantics. Atomic
sentences. Complex sentences. Quantifiers. Examples. FOL knowledge
base. Situation calculus.
• 13-First-order logic 2.
[AIMA Ch 7] Describing actions.
Planning. Action sequences.
DCP 1172, Lecture 1
Course Overview (cont.)
Representing and Organizing Knowledge
• 14/15-Building a knowledge base. [AIMA Ch 8] Knowledge bases.
Vocabulary and rules. Ontologies. Organizing knowledge.
An ontology
for the sports
domain
DCP 1172, Lecture 1
Course Overview (cont.)
Reasoning Logically
• 16/17/18-Inference in first-order logic. [AIMA Ch 9] Proofs. Unification.
Generalized modus ponens. Forward and backward chaining.
Example of
backward chaining
DCP 1172, Lecture 1
Course Overview (cont.)
Examples of Logical Reasoning Systems
• 19-Logical reasoning systems.
[AIMA Ch 10] Indexing, retrieval
and unification. The Prolog language.
Theorem provers. Frame systems
and semantic networks.
Semantic network
used in an insight
generator (Duke
university)
DCP 1172, Lecture 1
Course Overview (cont.)
Systems that can Plan Future Behavior
• 20-Planning. [AIMA Ch 11] Definition and goals. Basic representations
for planning. Situation space and plan space. Examples.
DCP 1172, Lecture 1
Course Overview (cont.)
Expert Systems
• 21-Introduction to CLIPS. [handout]
Overview of modern rule-based
expert systems. Introduction to
CLIPS (C Language Integrated
Production System). Rules.
Wildcards. Pattern matching.
Pattern network. Join network.
DCP 1172, Lecture 1
CLIPS expert system shell
Course Overview (cont.)
Logical Reasoning in the Presence of Uncertainty
• 22/23-Fuzzy logic.
[Handout] Introduction to
fuzzy logic. Linguistic
Hedges. Fuzzy inference.
Examples.
Center of gravity
Center of largest area
DCP 1172, Lecture 1
Course Overview (cont.)
AI with Neural networks
• 24/25-Neural Networks.
[Handout] Introduction to
perceptrons, Hopfield networks,
self-organizing feature maps.
How to size a network? What can
neural networks achieve?
x 1(t)
w1
x 2(t)
w
w
xn(t)

2
axon
n
DCP 1172, Lecture 1
y(t+1)
Course Overview (cont.)
Evolving Intelligent Systems
• 26-Genetic Algorithms.
[Handout] Introduction
to genetic algorithms
and their use in
optimization
problems.
DCP 1172, Lecture 1
Course Overview (cont.)
What challenges remain?
• 27-Towards intelligent machines. [AIMA Ch 25] The challenge of robots:
with what we have learned, what hard problems remain to be solved?
Different types of robots. Tasks that robots are for. Parts of robots.
Architectures. Configuration spaces. Navigation and motion planning.
Towards highly-capable robots.
• 28-Overview and summary. [all of the above] What have we learned.
Where do we go from here?
DCP 1172, Lecture 1
[email protected]