Professional Documents
Culture Documents
Introduction
Chapters 1
Big questions
Human
Rationality
performance
Thought process
and reasoning
Behavior
Views of AI
Like
humans Well
GPS Rational
Think agents
Heuristic
Act Eliza
systems
Thinking humanly: The Cognitive Modeling
Like
humans Well
• Reasons like humans do
– Programs that behave like humans Think GPS Rational
agents
• Requires understanding of the internal
Heuristic
activities of the brain Act Eliza
systems
GPS Rational
Think agents
AI tends to
work mostly
in this area
Heuristic
Act Eliza
systems
Turing Test
• “ Can machines think?” “can machines behave intelligently?”
• The operational test for the intelligence behavior: the imitation game
Computer
Science &
Mathematics Engineering Philosophy
Economics
AI Biology
Psychology Linguistics
Cognitive
Science
Foundation …
History of AI
• Traditional paradigms:
Programs = data structure + algorithm
• AI programming paradigms:
Programs = knowledge structure + inference mechanism
Sub-fields of Artificial Intelligence
• AI now consists many sub-fields, using a variety of techniques,
such as:
– Neural Networks – e.g. brain modeling, time series prediction, classification
– Evolutionary Computation – e.g. genetic algorithms, genetic programming
– Vision – e.g. object recognition, image understanding
– Robotics – e.g. intelligent control, autonomous exploration
– Expert Systems – e.g. decision support systems, teaching systems
– Speech Processing– e.g. speech recognition and production
– Natural Language Processing – e.g. machine translation
– Planning – e.g. scheduling, game playing
– Machine Learning – e.g. decision tree learning, version space learning
• Most of these have both engineering and scientific aspects.
Computer Science VS Artificial Intelligence
• Computer Science
– Methods for applying computers to problems
– Study of the fundamental limits of computation
• Artificial Intelligence
– Methods for applying computers to problems that require
“intelligence”
– Study of the fundamental limits of “intelligent” behavior by
computers
Prolog
Introduction to Prolog
• It is a declarative language
• Used in AI applications such as NLP, automated reasoning systems, expert systems,
…
• Prolog is based on facts, rules, queries, constants and variables.
– Facts and rules make up the database.
– Constants and variables are used to construct facts, rules and queries.
– Queries drive the search processes
Syntax
Prolog files are with extension .pl. They contain :
Facts: example,
male(sam).
male(john).
child(sam,john).
Rules: to combine facts to increase knowledge of the system
son(X,Y):- male(X),child(X,Y).
– X is a son of Y if X is male and X is a child of Y
Logical connectives
Syntax Example:
PL/FOL Prolog PL/FOL Prolog
Query:
?- likes(sam,chips).
?- likes(sam,X).
Reading Assignment
1. Read and list out the contribution of various disciplines to
the foundation of Artificial Intelligence (AI) to exist as a
science?
2. What are the potted history of AI? Read more about the
technological evolution related to AI (state of the art)
3. Read about the following topics
– Computer Vision
– Robotics
– Expert Systems (knowledge based systems)
– Natural Language Processing
– Knowledge representation (knowledge management)
– Machine Learning
– Neural Networks
4. What an AI system can and cannot do?