3. AI : a branch of computer science dealing with
the simulation of intelligent behavior in
computers
AI : the capability of a machine to imitate
intelligent human behavior
4. AI : Field of Computer science that has many
intersections with the domains of cognitive
sciences, logic, linguistics, etc.
Computer Sciences
Database
Software
Engineering
Artificial
Intelligence
Human Sciences
Cognitives
Sciences
Sociology
5. Goal : Conceive and design Systems that:
◦ Think& act like humans
◦ Think & act rationally
Thinking rationally : what are correct
arguments/thought processes?
Acting rationally : rational behavior : doing the
right thing
The right thing: which is expected to maximize
goal achievement, given the available
information
6. ⇨ Rational agents
An agent is an entity that perceives and acts
Abstractly, an agent is a function from percepts
histories to actions:
f : P* → A
For any given class of environments and tasks,
we seek the agent (or class of agents) with the
best performance
Design the best program for given machine
resources according to the studied environment
7. AI research tends to make the machine intelligent.
A smart machine is equipped with intelligent
programs for :
◦ Visual and auditory perception,
◦ Comprehension (text or dialogue in natural language),
◦ Knowledge processing
◦ Reasoning,
◦ Learning,
◦ Decision making,
◦ Solving difficult problems (complex and NP-hard problems,
static and dynamic combinatorial problems, mono-objective
or multi-objectives optimization problems),
◦ Interacting with the environment (acquire information and
proposing a decision or an action plan)
8. Goals :
◦ study and simulation of human intellectual
activities in situations where a classical
algorithmic solution is not available
◦ model the reasoning modes of a human expert
and make them accessible to a non-computer
scientist.
9. 1. AI Pre-history
- Among the first problems addressed : Automatic
translation
- The failure led to questions about:
- The representation to be given to knowledge
- How to "extract" this knowledge from an
individual
10. 2. AI beginnings (1955 - 1970)
◦ 1956: AI: name born at a congress in Dartmouth by
two researchers: John McCarthy & Marvin Minsky
◦ 1959: Development of a General Problem Solver
(GPS) system based on the assessment of the
difference between the current situation of the
system and the goal to be achieved.
◦ 1960: McCarthy develops LISP language : the
language of the AI for the next 20 years.
11. ◦ Early 60s: Samuel and Bernstein develop the first
program for playing chess
◦ 1965: Appearance of ELIZA system of automatic
production of speech in natural language
◦ 1969: DENDRAL, one of the first expert systems
(analysis of a mass spectrography in chemistry)
12. 3. Specialization (1970 → …)
◦ Appearance of PROLOG language
◦ Speech recognition and understanding (HEARSAY,
blackboard)
◦ MYCIN: Expert system on bacterial infections (IF-
THEN rules and certainty coefficients, separation
of expert knowledge and inference engines)
◦ Other Expert Systems in industry, in medical
diagnosis, etc.
◦ Automatic Theorem Proof
◦ Games
◦ Knowledge Representation
◦ Perception
◦ Learning
◦ Big Data trends
13. Autonomous planning (NASA), logistics (Army)
Traffic planning (transportation companies : road and
air)
Voice recognition and synthesis
Image recognition and synthesis (face recognition)
Writing recognition (Check signature, postal code)
Games (AlphaGo, chess, etc.)
Automatic control (self-driving cars)
Diagnostic (expert level, in Medicine)
Robotics in industry, aerospace, etc.
Smart home,
Driving assistance,
Image recognition to unlock,
Personal assistants (Iphone, Samsung, etc.),
14. Programming Language
◦ Lisp (1960, J. MacCarthy)
◦ SmallTalk (1972, A. Kay)
◦ Prolog (1973, A. Colmerauer),
◦ Prolog with constraints
◦ JAVA (1994) ,
◦ C++,
◦ Scheme, ...
Agent Plateforms
◦ IBM Aglets,
◦ JADE,
◦ Jbuilder,
◦ Madkit, etc.