Artificial Intelligence

Lect. (1)
Dr. Nader A. Mansour
[email protected]
Mechanical Engineering Department
Assessment

Mid-Term Exam >> 30

Attendance & Assignments >> 15
Project >> 15
Final Exam >> 90

Software
MATLAB.
Course Content

Introduction to Artificial Intelligence techniques.

Expert Systems.
Fuzzy Logic Controllers.
Adaptive Neuro-Fuzzy Inference Systems (ANFIS).
Genetic Algorithm.
Neural Network.
References
Outlines
What is Intelligence?
What is AI?
why to study AI?
Fields of AI
Industrial Applications of AI
Advantages of using AI
Where AI should/ shouldn’t be applied?
Soft Computing Vs. Hard Computing
What is Intelligence?

The ability to learn or understand things or to deal with

new or difficult situations.
(Webster's dictionary)

The capability of a system to adapt its behavior

(implement decisions) to meet its goals in a range of
environments. It is a property of all purpose-driven
decision makers.
(David Fogel)
What is Artificial Intelligence?
System that think like human … ( General Problem Solver)
 [The automation of] activities that we associate with human
thinking, activities such as decision-making, problem solving,
learning... (Bellman, 1978)
System that think rationally … ( The Laws of Thought
Approach)
 The art of creating machines that perform functions that
require intelligence when performed by people (Kurzweil,
1990)
 Ex,
All humans are mortal, Mohamed is a human, Mohamed is
mortal
What is Artificial Intelligence?
System that act like human … (Turing Test Approach)
 The study of the computations that make it possible to
perceive, reason, and act (Winston, 1992)
 Turing test, Marcus test, Lovelace test, Reverse Turing test
“CAPTCHA system”
System that act rationally … (Rational Agent Approach)
 The branch of computer science that is concerned with the
automation of intelligent behavior (Luger and Stubblefield
1993)
What is Artificial Intelligence?

Rationality is the ideal concept of intelligence. System is

rational if it is doing the right thing.

This doesn’t mean that human is irrational. But humans

sometimes make mistakes for example;
Not everyone gets A on exams.
Chess game playing, people may make mistakes although
they know the rules very well.
What is Artificial Intelligence?

AI is a study about inventing machines/computers that

capable of mimicking human/animal intelligent behavior.
The ultimate objective is to develop a system that can
think and act rationally and like humans.
AI is a “tool” that has been developed to imitate human
intelligence and decision-making functions, providing
basic reasoning and other human characteristics.
Why to study AI?
To learn more about ourselves.
Machines with human-level intelligence would have a huge
impact on our everyday lives and the future of civilization.
AI encompass huge variety of subfields from general
purpose areas such as perception and logical reasoning to
specific tasks such as game playing, theorem proving and
diagnosing diseases. (Game Playing in AI … REPORT!)
 Building algorithms/hardware that is based on human/animal
intelligence (Copying from biological systems).
Why to study AI?
 Copying from biological systems
Why to study AI?
 Copying from biological systems
Why to study AI?
 Copying from biological systems
Fields of AI
 Expert System
 Natural language processing
 Speech (voice) understanding/ recognition
 Robotic & Sensor system
 Text and face recognition
 Intelligent computer aided instruction
 Neural computing
 Machine learning
 Fuzzy logic
 Genetic algorithms
 Intelligent agent
Industrial Applications of AI
Industrial Applications of AI
 Assignment …
Search for available products that uses AI techniques in the
market.
Advantages of using AI
 Better performance
 Longer Life
 Reliability
 Simpler operation
 Cost effective
 Higher efficiency
 Self-organizing / self-optimization
 Simpler design.
Where AI should be applied?
 Data is overwhelming/abundance
 Too many manual operations/procedures
 Optimization is possible
 Decision making is required
 When current techniques are too complicated to be
used/designed
 Mathematical models are too complex/impossible
 To increase efficiency
 To reduce cost
 To improve performance and reliability
Where AI should not be applied?
 Lack of Data
 Simpler techniques are available / sufficient
 Further optimization is not possible
Soft Computing
 The concept of Soft Computing (SC) was first initiated by Lotfi
Zadeh in 1981.
 Soft Computing definition by Lotfi Zadeh …
“Soft Computing is an emerging approach to computing which
parallel the remarkable ability of the human mind to reason and
learn in an environment of uncertainty and imprecision”
 Zadeh, defined the SC as one multidisciplinary system as the
fusion of the fields of Fuzzy logic, Neuro-Computing,
Evolutionary and Genetic Computing and Probabilistic
Computing.
Soft Computing
 SC is the fusion of methodologies designed to model and
enable solutions to real world problems which are not modeled
or too difficult to be model mathematically.
 The aim of SC is to exploit the tolerance for imprecision,
uncertainty, approximate reasoning and partial truth in order to
achieve resemblance to human like decision making.
 SC consist of several computing paradigms mainly;
Fuzzy Logic (FL) … (Reasoning and Knowledge Representation)
Neural Network (NN) … (Learning)
Genetic Algorithms (GA) … (Optimization)
Soft Computing
 SC can be seen as
Soft Computing
 Hybridization of the three main paradigms (FL, NN and GA)
creates a successful synergic effect that creates a situation
where different entities cooperate advantageously for a final
outcome.
 Soft Computing (Goals)
 The main goal of the SC is to develop intelligent machines to provide
solutions to real world problems which are not modeled or too
difficult to model mathematically.
 Its aim is to exploit the tolerance for imprecision, uncertainty,
approximate reasoning and partial truth in order to achieve resemblance
to human like decision making.
Approximation
The model features are similar to the real one, but not the same
Uncertainty
We are not sure that the features of the model are same as the entity
Imprecision
The model features are not the same as the real ones, but close to them
 Soft Computing (Importance)
 The main benefit of SC that it exploits the tolerance of imprecision,
approximation and uncertainty to achieve robustness and low cost
solution. In fact, the role model for SC is the human mind.
 Soft Computing is a partnership among different techniques in which
each of the partners contributes a distinct methodology for addressing
problems in its domain.
 In other words … the participating methodologies are complementary
rather than competitive
Hard Computing
 conventional computing, requires a precisely stated analytical
model and often a lot of computation time
 based on binary logic, crisp systems, numerical analysis and
crisp software
 has the characteristics of precision
Soft Computing Vs. Hard Computing
 Hard computing requires programs to be written; soft computing
can evolve its own programs
 Hard computing uses two-valued logic; soft computing can use
multivalued or fuzzy logic
 Hard computing is deterministic; soft computing can be stochastic
 Hard computing requires exact input data; soft computing can deal
with ambiguous and noisy data
 Hard computing is strictly sequential; soft computing allows
parallel computations
 Hard computing produces precise answers; soft computing can
yield approximate answers
References
 Ahmed Ramadan lecture notes.
 Artificial Intelligence: A Modern
Approach