Download CSC 480: Artificial Intelligence - An

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Wizard of Oz experiment wikipedia , lookup

Human-Computer Interaction Institute wikipedia , lookup

Computer vision wikipedia , lookup

Ecological interface design wikipedia , lookup

Human–computer interaction wikipedia , lookup

Technological singularity wikipedia , lookup

Incomplete Nature wikipedia , lookup

Agent-based model wikipedia , lookup

Artificial intelligence in video games wikipedia , lookup

Computer Go wikipedia , lookup

Expert system wikipedia , lookup

Embodied cognitive science wikipedia , lookup

Intelligence explosion wikipedia , lookup

AI winter wikipedia , lookup

Knowledge representation and reasoning wikipedia , lookup

Cognitive model wikipedia , lookup

Existential risk from artificial general intelligence wikipedia , lookup

Ethics of artificial intelligence wikipedia , lookup

Philosophy of artificial intelligence wikipedia , lookup

History of artificial intelligence wikipedia , lookup

Transcript
Introduction
1
24 May 2017
ARTIFICIAL INTELLIGENCE
EXAMPLES OF DEFINITIONS OF AI

approaches
emphasis on the way systems work or “think”
 Behavioral

approaches
only activities observed from the outside are taken into
account
 Human-like

24 May 2017
 Cognitive
systems
try to emulate human intelligence
 Rational
systems
systems that do the “right thing”
 idealized concept of intelligence

2
SYSTEMS THAT THINK LIKE HUMANS

“[The automation of] activities that we associate
with human thinking, activities such as decisionmaking, problem solving, learning …”
[Bellman, 1978]
24 May 2017

“The art of creating machines that perform
functions that require intelligence when performed
by people”
[Kurzweil, 1990]
3
SYSTEMS THAT THINK RATIONALLY
study of mental faculties through the
use of computational models”
[Charniak and McDermott, 1985]
24 May 2017
 “The
 “The
study of the computations that make
it possible to perceive, reason, and act”
[Winston, 1992]
4
SYSTEMS THAT ACT RATIONALLY
field of study that seeks to explain and
emulate intelligent behavior in terms of
computational processes”
[Schalkhoff, 1990]
24 May 2017
 “A
 “The
branch of computer science that is
concerned with the automation of
intelligent behavior”
[Luger and Stubblefield, 1993]
5
COGNITIVE MODELING
to construct theories of how the
human mind works
24 May 2017
 Tries
 Uses
computer models from AI and
experimental techniques from psychology
 Most
AI approaches are not directly based
on cognitive models


often difficult to translate into computer programs
performance problems
6
RATIONAL THINKING

on abstract “laws of thought”
24 May 2017
 Based
usually with mathematical logic as tool
 Problems
and knowledge must be
translated into formal descriptions
 The
system uses an abstract reasoning
mechanism to derive a solution
 Serious
real-world problems may be
substantially different from their abstract
counterparts
7
RATIONAL AGENTS
agent that does “the right thing”
24 May 2017
 An
it achieves its goals according to what it knows
 perceives information from the environment
 may utilize knowledge and reasoning to select actions

8
BEHAVIORAL AGENTS
agent that exhibits some behavior
required to perform a certain task
24 May 2017
 An
may simply map inputs onto actions
 simple behaviors may be assembled into more
complex ones

9
FOUNDATIONS OF ARTIFICIAL INTELLIGENCE

theories of language, reasoning, learning, the mind
24 May 2017
 Philosophy
 Mathematics

formalization of tasks and problems (logic, computation,
probability)
 Linguistics
understanding and analysis of language
 knowledge representation

 Psychology
10
FOUNDATIONS OF ARTIFICIAL INTELLIGENCE
CONT.




science
provides tools for testing theories
programmability
speed
storage
24 May 2017
 Computer
11
CONCEPTION (LATE 40S, EARLY 50S)
neurons (McCulloch and Pitts,
1943)
 Learning
 Chess
24 May 2017
 Artificial
in neurons (Hebb, 1949)
programs (Shannon, 1950; Turing,
1953)
 Neural
computer (Minsky and Edmonds,
1951)
12
BABY STEPS (LATE 1950S)
of programs solving simple
problems that require some intelligence
 Development
24 May 2017
 Demonstration
of some basic concepts and
methods
Lisp (McCarthy, 1958)
 formal methods for knowledge representation and
reasoning

13
(EARLY 1960S)
Problem Solver (Newell and
Simon, 1961)
 Shakey
24 May 2017
 General
the robot (SRI)
 Algebraic
problems (Bobrow, 1967)
 Neural
networks (Widrow and Hoff, 1960;
Rosenblatt, 1962; Winograd and Cowan,
1963)
14
(LATE 60S, EARLY 70S)
networks can learn, but not very
much (Minsky and Papert, 1969)
24 May 2017
 Neural
 Expert
systems are used in some real-life
domains
 Knowledge
representation schemes
become useful
15
AI GETS A JOB (EARLY 80S)

applications of AI systems
R1 expert system for configuration of DEC computer
systems (1981)
 Expert
 AI
24 May 2017
 Commercial
system shells
machines and tools
16
(LATE 80S)
all, neural networks can learn more
in multiple layers (Rumelhart and
McClelland, 1986)
24 May 2017
 After
 Hidden
Markov models help with speech
problems
17
(90S)
 AI
and speech recognition work
24 May 2017
 Handwriting
is in the driver’s seat (Pomerleau, 1993)
18
INTELLIGENT AGENTS APPEAR (MID-90S)
between hardware (robots) and
software (softbots)
 Agent
architectures
 Situated

24 May 2017
 Distinction
agents
embedded in real environments with continuous
inputs
 Web-based
agents
19
CHAPTER SUMMARY
to important concepts and
terms
 Relevance
 Influence
24 May 2017
 Introduction
of Artificial Intelligence
from other fields
 Historical
development of the field of
Artificial Intelligence
20