Computational Intelligence (CI)
Introduction
[Module 1]
Dr. Dayal Kumar Behera
School of Computer Engineering
KIIT Deemed to be University, Bhubaneswar, India
OSGN - OSPN [1]
Motivation
New world of computation:
• Mobility: Computation is everywhere
• Dynamic: Computation for everything
• Adaptation and Improvement: Computation in every environment
• Uncertainty and Noise
• Missing Information
OSGN - OSPN [2]
Computing ?
Computing
Input Output
y = f(x)
Antecedent Consequent
y = f (x), f is a mapping function/algorithm to solve a problem
Computing is a mapping function.
It is basically the algorithm to solve a problem.
OSGN - OSPN [3]
Characteristics of Computing
➢ Should provide precise solution
➢ Control action should be unambiguous and accurate
➢ Control action is formally defined (with mathematical model or algorithm)
OSGN - OSPN [4]
Hard Computing
➢ In 1996, Lotfi A. Zadeh introduces the term hard computing.
➢ According to Zadeh, a computing is called hard computing if
o Precise result is guaranteed.
o Control action is unambiguous.
o Control action is formally defined.
OSGN - OSPN [5]
What is Soft Computing?
➢ The Term Soft Computing (SC) was proposed by the inventor of fuzzy logic, Lotfi A.
Zadeh, 1992.
➢ The idea of soft computing was initiated in 1981 when Lotfi A.
Zadeh published his first paper on soft data analysis “What is
soft computing”, soft computing Springer-Verlag Germany/USA
1997.
➢ Zadeh, defined Soft Computing into one multidisciplinary
system as the fusion of the fields of Fuzzy Logic, Neuro-
Computing, Evolutionary and Genetic Computing, and
Probabilistic Computing.
Lotfi A. Zadeh
➢ Soft Computing is the fusion of methodologies designed to
model and enable solutions to real world problems, which are
not modelled or too difficult to model mathematically.
OSGN - OSPN [6]
What is Soft Computing?
➢ Lotfi A. Zadeh describes Soft Computing (SC) as follows.
Soft computing is an emerging approach to computing which
parallels the remarkable ability of the human mind to reason
and learn in an environment of uncertainty and imprecision.
It is characterized by the use of inexact solutions to computationally hard
tasks.
OSGN - OSPN [7]
Terminology
Approximation: similar to the real ones, but not the same.
Uncertainty: lack of sureness.
What will happen next, this is an example of uncertainty.
Outcome of tossing a coin – head or tail (not sure/doubt)
Imprecision/Vagueness: lack of clarity
Is hot? Vague as there is no particular temp that represents hot.
Tall? Vague as there is no well defined boundary that represents tall
Ambiguity: more than one interpretation/inexactness
Bank – can refer to a financial institution or riverside
OSGN - OSPN [8]
Characteristics of Soft Computing
➢ Soft computing is tolerant of imprecision, uncertainty and approximation
➢ Algorithms are adaptive (i.e. it can adjust to the change of dynamic
environment)
➢ Uses evolutionary computing (biologically inspired methodologies) to
find optimal solution
OSGN - OSPN [9]
Soft Computing Paradigms?
OSGN - OSPN [10]
Soft Computing Paradigms/Constituents
Soft computing consists of several computing paradigms mainly:
➢ Fuzzy Systems- for knowledge representation via fuzzy If Then rules.
➢ Neural Networks- for learning and adaptation
➢ Genetic Algorithms- for evolutionary computation for search and optimization
Sometimes, Hybridization of these three fields increases the strength of the
system.
OSGN - OSPN [11]
Example 1
➢ How a student learns from his teacher?
o Teacher asks questions and tells the answers.
o Teacher puts questions and hints answers and asks whether the
answers are correct or not
o student thus learns a topic and stores in his memory
o Based on the knowledge the student solves new problems
➢ This is the way how human brain works.
➢ Artificial Neural Network is used to solve problems.
Ability to learn, memorize and
still generalize
OSGN - OSPN [12]
Example 2
➢ How world selects the best?
o It starts with a random population
o Reproduces another population (next generation)
o Rank the population and selects the best
➢ Genetic Algorithm is based on this natural phenomena.
o Population is synonymous to solutions.
o Selection of best solution is synonymous to finding the optimal
solution.
OSGN - OSPN [13]
Example 3
➢ How a doctor treats his patient ?
o Doctor asks the patient about suffering.
o Doctor find symptoms of diseases.
o Doctor prescribed tests and medicines.
➢ This is how fuzzy logic works.
o Symptoms are correlated with diseases with uncertainty.
o Doctor prescribes tests/medicines fuzzily
OSGN - OSPN [14]
Example
A neural character recognizer and a knowledge base responding
to three hand-written characters that form a word "dog."
OSGN - OSPN [15]
Soft Computing vs. Hard Computing
Hard Computing Soft Computing
Conventional computing that requires a Soft Computing is tolerant of
precisely stated analytical model. imprecision and uncertainty.
Often requires a lot of computation time Can solve some real-world problems in
for real-world problem. reasonably less time.
Not suited for real-world problems for Suitable for real-world problems.
which ideal model is not present.
It requires full truth. Can work with partial truth.
It is precise and accurate Imprecise
It is known for Conventional AI. It is known for Computational
Intelligence
OSGN - OSPN [16]
Soft Computing Strength
CI
AI
OSGN - OSPN [17]
Hybrid Computing
It is a combination of conventional hard computing and emerging soft
computing.
OSGN - OSPN [18]
Intelligence
• ability to learn or understand the environment.
• ability to solve complex problems or make decisions.
Artificial intelligence (AI) is the intelligence of machines or software.
OSGN - OSPN [19]
Motivation for CI: Nature Inspired
• Nature for Computation: CI
• Computation for nature: Computational Biology
OSGN - OSPN [20]
History
OSGN - OSPN [21]
Definition
Computational Intelligence (CI):
• Is a sub-branch of AI.
• Is a set of nature-inspired computational methodologies and approaches.
• Solves complex real-world problems to which traditional approaches are
ineffective or infeasible.
• Study of adaptive mechanisms to enable or facilitate intelligent behavior in
complex and changing environments. (Engelbrecht, 2007).
OSGN - OSPN [22]
Pseudonym of CI
Pseudonym : a fictitious name, especially one used by an author.
• Soft Computing
• Natural Computation
• Nature-Inspired Computing
• Adaptive Systems
Note# Even though it is commonly considered a synonym of soft computing,
there is still no commonly accepted definition of computational intelligence.
OSGN - OSPN [23]
AI vs CI
Artificial Intelligence (AI) is an area of computer science which focuses on the
development of intelligent machines, and Computational Intelligence (CI) is a sub-field
within AI that focuses on creating systems capable of performing complex tasks.
Source: https://link.springer.com/chapter/10.1007/978-3-030-67921-7_1
OSGN - OSPN [24]
AI vs CI
OSGN - OSPN [25]
General Intelligence
General Intelligence: to perform intellectual task that a human can.
OSGN - OSPN [26]
CI Modeling Methodology
OSGN - OSPN [27]
Applications of CI
Few applications are listed below
OSGN - OSPN [28]
Application Domain of CI
Some application domains are
OSGN - OSPN [29]
CI as a Service
OSGN - OSPN [30]
Future of CI
• Hybrid Systems
• New techniques/algorithms
• Ubiquitous and pervasive computing
• Smart IoT device
• And others..
OSGN - OSPN [31]
Thank you
OSGN - OSPN [32]
