CHAPTER -1

Introduction

For Electrical and computer

engineering department
Prepared by : Hayleyesus
Girma(Msc)
Grading
• Quiz-1 (5%)
• Quiz-2 (5%)
• Assignment(10%)
• Assignment(10%)
• Midterm-exam(20%)
 Introduction to intelligent control
• Conventional control uses theories and the methods, that have
developed in the past decades, of which is primarily described by
differential equations.
• Intelligent control attempts to enhance conventional control to solve
new challenging control problems.
• It uses conventional control methods to solve "lower level" control
problems. That is, conventional control is included in the area of
intelligent control.
• Intelligent control means some form of control using fuzzy, neural
network and/or optimization techniques. However Intelligent control
does not restrict only to those techniques.
 Introduction to intelligent control

• There are three fundamental characteristics in intelligent control

systems.
• Adaptation and Learning
• The ability to adapt to changing conditions is necessary in an
intelligent system.
• The ability to learn, for systems to be able to adapt to a variety of
unexpected changes is essential.
 Introduction to intelligent control
• Autonomy and Intelligence
• Autonomy in achieving goals is an important characteristic of
intelligent control systems. When a system has the ability to act
appropriately in an uncertain environment for periods of time without
external intervention, it is considered to be highly autonomous. An
adaptive controller is higher autonomous than a fixed controller.
• Although for low autonomy no intelligence (or "low" intelligence) is
necessary, for high degrees of autonomy, intelligence in the system is
essential.
 Introduction to intelligent control

• Structures and Hierarchies

• In order to cope with complexity, an intelligent system must have an
appropriate functional structure for efficient analysis and evaluation of
control strategies.
• Hierarchies (that may be localized or combined in hierarchies) that
may serve for such structures to cope with complexity.
 What is Intelligence System
• Ability of a system to adapt its behavior to meet its goal in a range of
environments.
• Intelligent systems generally can acquire and apply knowledge
in an “intelligent” manner and have the capabilities of
perception, reasoning, learning, and making inferences (or
decisions) from incomplete information.
Who is smarter you or the computer?
• The answer is increasingly complex and depends on definitions in
flux.
• Today, computers can learn faster than humans.
• E.g., (IBM’s) Watson can read and remember all the cancer research,
no human could.
• How it is possible?
 Artificial Intelligence (AI)

• Refers to the simulation of human intelligence in machines that are

programmed to think like humans and mimic their actions.
• Most AI examples that you hear about today from chess-playing
computers to self-driving cars.
• “A chess-playing supercomputer, made history in 1997 when it
defeated reigning world champion Garry Kasparov in a six-game
match.”
• What is AI
• The ability to learn/ understand/ deal with new situations.
 Computational Intelligence(CI)
• Computational Intelligence is a subset of AI.
• CI is a synonym for soft computing.
• Computational Intelligence (CI) usually refers to the ability of a
computer to learn a specific task from data or experimental
observation.
• CI comprises practical adaptation and self-organization concepts,
paradigms, algorithms, and implementation that enable or facilitate
appropriate actions (intelligent behavior) in a complex and changing
environment.
• CI is concentrated on the study of adaptive mechanisms to enable
intelligent behavior in complex and changing environments.
CI paradigms
 Soft computing (CI) vs Hard Computing

• Soft computing is based on the model of the human mind where it

has probabilistic reasoning, and fuzzy logic and uses multivalued logic.
• Example: computer-aided diagnosis in medical and hand writing
recognition in fraud detection.
• Hard Computing relies on binary logic and predefined instructions
like a numerical analysis and uses two-valued logic
• Example: conventional algorithms are merge sort, quick sort, binary
search, greedy algorithm, dynamic programming, etc.
 Soft Computing
• Zadeh perspective on intelligent systems (in 1962): “I believe the
system analysis and controls should embrace soft computing and
assign a higher priority to the development of methods that can cope
with imprecision, uncertainties, and partial truth.”
• Utilization of the human brain as a role model in the decision-making
processes, can be regarded as the foundation of intelligent systems
design methodology.
• In contrast to analytical methods, soft computing methodologies
mimic consciousness and cognition in several important respects: they
can learn from experience; they can universalize into domains where
direct experience is absent; and, through parallel computer
architectures that simulate biological processes, they can perform
mapping from inputs to the outputs.
Soft Computing vs Hard Computing

Soft Computing (CI) Hard Computing

Tolerant to imprecision, uncertainty, Precisely stated analytical model.
partial truth, and approximation.
Fuzzy logic, neural Networks, Based on binary logic, crisp system,
probabilistic reasoning numerical analysis, and crisp software.
Evolve their own programs Programs are to be written
Multi-valued logic Two valued logic
Ambiguous and noisy data Exact input data
Parallel computation Strictly Sequence
Approximate answers Precise answers
 CI vs AI

Computational Intelligence(CI) Artificial Intelligence(AI)

Soft Computing Technique Hard Computing Technique

Follow Fuzzy Logic Follow Binary Logic

Nature Inspired Models Based on Mathematical Models

Can Work in Exact and Incomplete Data Not Very Effective
Probabilistic Result Deterministic Result
 Applications of CI

• Real-time water treatment process control with ANN.

• Classification and diagnostic prediction of cancers.
• Hybrid approach to solve the team allocation problem.
• Regression testing prioritization based on FIS.
• Classification of Social network users.
• Power system harmonics estimation.
• Hydrothermal power systems operation planning.
• Sentiment Classification.
• Improving the performance of IOT Application
Application of CI in real-world problems
• Robotics
• Natural Language Processing
• Facial and Speech Recognition
• Game Playing
• Health Care
• Finance and Banking
• Machine Learning
• Military Equipment
Top companies working with CI
• Amazon
• Facebook
• Google