SOFT COMPUTING

BY

PROF. MAYURI BAPAT

• Soft computing is the reverse of hard
(conventional) computing. It refers to a group
of computational techniques that are based on 
artificial intelligence (AI) and natural selection.
It provides cost-effective solutions to the
complex real-life problems for which hard
computing solution does not exist.
• Zadeh coined the term of soft computing in
1992. The objective of soft computing is to
provide precise approximation and quick
solutions for complex real-life problems.
• In simple terms, you can understand soft
computing - an emerging approach that gives
the amazing ability of the human mind. It can
map a human mind and the human mind is a
role model for soft computing.
 1)      Hard computing, i.e., conventional computing, requires a precisely stated analytical
Difference model and often a lot of computation time. Soft computing differs from conventional (hard)
computing in that, unlike hard computing, it is accepting vagueness, uncertainty, partial truth,
between hard and approximation. In effect, the role model for soft computing is the human mind. 
2)      Hard computing based on binary logic, crisp systems, numerical analysis and crisp
computing & software but soft computing based on fuzzy logic, neural nets and probabilistic reasoning. 

soft computing 3)      Hard computing has the characteristics of accuracy and categoricity and the soft
computing, approximation and dispositionality. Although in hard computing, vagueness and
uncertainty are undesirable properties, in soft computing the tolerance for imprecision and
uncertainty is exploited to achieve tractability, lower cost, high Machine Intelligence
Quotient (MIQ) and economy of communication 
4)      Hard computing requires programs to be written; soft computing can evolve its own
programs 
5)      Hard computing uses two-valued logic; soft computing can use multivalued or fuzzy
logic 
6)      Hard computing is deterministic; soft computing incorporates randomness 
7)      Hard computing requires exact input data; soft computing can deal with ambiguous
and noisy data 
8)      Hard computing is strictly sequential; soft computing allows parallel computations 
9)      Hard computing produces precise answers; soft computing can yield approximate
answers 
FUZZY LOGIC
 Definition of fuzzy logic
• Fuzzy Logic (FL) is a method of reasoning that look
like human reasoning. The approach of FL replicates
the way of decision making in humans that involves all
intermediate possibilities between digital values YES
and NO.
• The conventional logic block that a computer can
understand takes precise input and produces a definite
output as TRUE or FALSE, which is equivalent to
human’s YES or NO.
• The inventor of fuzzy logic, Lotfi Zadeh, observed that
unlike computers, the human decision making includes
a range of possibilities between YES and NO, such as
− CERTAINLY  YES
POSSIBLY YES
CANNOT SAY
POSSIBLY NO
CERTAINLY NO
• The fuzzy logic works on the levels of
possibilities of input to achieve the definite
output.
 • Application areas of fuzzy logic

Vehicle Consumer
Automotive Automatic Four-Wheel
environment Electronic
Systems Gearboxes Steering
control Goods

Still and
Hi-Fi Systems Photocopiers Video Television
Cameras
• Domestic Goods
• Microwave Ovens
• Refrigerators
• Toasters
• Vacuum Cleaners
• Washing Machines
• Environment Control
• Air Conditioners/Dryers/Heaters
• Humidifiers: Humidifier therapy adds moisture to the
air to prevent dryness that can cause irritation in many
parts of the body.
• Advantages of fuzzy logic

You can modify a FLS by

Mathematical concepts
just adding or deleting
within fuzzy reasoning
rules due to flexibility of
are very simple.
fuzzy logic.

Fuzzy logic Systems can

FLSs are easy to
take imprecise, distorted,
construct and understand.
noisy input information.

Fuzzy logic is a solution to complex problems in all

fields of life, including medicine, as it resembles human
reasoning and decision making.
 • Disadvantages OF FUZZY LOGIC

There is no systematic They are understandable only They are suitable for the
approach to fuzzy system when simple. problems which do not need
designing. high accuracy.
NEURAL NETWORK 
• What are artificial
neural networks
(anns)? • The inventor of the first neurocomputer,
Dr. Robert Hecht-Nielsen, defines a
neural network as −
• "...a computing system made up of a
number of simple, highly interconnected
processing elements, which process
information by their dynamic state
response to external inputs.”
Definition

• Neural networks are mathematical models that

use learning algorithms inspired by the brain to
store information. Since neural networks are
used in machines, they are collectively called
an ‘artificial neural network.’ 
• Advantages of
neural networks There are various advantages of neural networks, some of which are
discussed below:

1) Store information on the entire network: Just like it happens in

traditional programming where information is stored on the network
and not on a database. If a few pieces of information disappear from
one place, it does not stop the whole network from functioning.

2) The ability to work with insufficient knowledge: After the

training of ANN, the output produced by the data can be incomplete
or insufficient. The importance of that missing information
determines the lack of performance.

3) Good fault tolerance: The output generation is not affected by

the corruption of one or more than one cell of artificial neural
network. This makes the networks better at tolerating faults.
4) distributed memory: for an artificial 6) Ability to train 7) The ability of parallel
neural network to become able to learn, it
is necessary to outline the examples and to
machine: ANN learn from processing: these networks
teach it according to the output that is events and make decisions have numerical strength which
desired by showing those examples to the through commenting on similar makes them capable of
network. The progress of the network is
directly proportional to the instances that
events. performing more than one
are selected. function at a time.
 The neural network needs training to
operate.

What are the The architecture of a neural network is

limitations of different from the architecture of
microprocessors. Therefore, simulation
neural is necessary.

networks?
Requires high processing time for large
neural networks.
• APPLICATIONS OF
NEURAL NETWORKS
• Character Recognition - The idea of
character recognition has become very
important as handheld devices like the Palm
Pilot are becoming increasingly popular.
Neural networks can be used to recognize
handwritten characters.
• Image Compression - Neural networks can
receive and process vast amounts of information
at once, making them useful in
image compression. With the Internet explosion
and more sites using more images on their sites,
using neural networks for image compression is
worth a look. 
• Stock Market Prediction - The day-to-
day business of the stock market
is extremely complicated.
Many factors consider in whether a given
stock will go up or down on any given day.
Since neural networks can examine a
lot of information quickly and sort it all
out, they can be used to predict stock
prices. 
• Traveling Saleman's
 Problem - Interestingly enough,
neural networks can solve
the traveling
salesman problem, but only to a
certain degree of approximation. 
• Aerospace − Autopilot aircrafts, aircraft fault
detection.
• Automotive − Automobile guidance systems.
• Military − Weapon orientation and
steering, target tracking, object
discrimination, facial recognition,
signal/image identification.
• Speech − Speech recognition, speech
classification, text to speech conversion.
• Anomaly Detection − As ANNs are expert at recognizing patterns, they can
also be trained to generate an output when something unusual occurs that
misfits the pattern.
• Industrial − Manufacturing process control,
product design and analysis, quality inspection
systems, welding quality analysis, paper
quality prediction, chemical product design
analysis, dynamic modelling of chemical
process systems, machine maintenance
analysis, project bidding, planning, and
management.
• NEURAL NETWORKS SCOPE

• It has a wide scope in the future. Researchers are constantly working on new
technologies based on neural networks. Everything is converting into
automation; hence they are very much efficient in dealing with changes and
can adapt accordingly. Due to an increase in new technologies, there are
many job openings for engineers and neural network experts. Hence in future
also neural networks will prove to be a major job provider.
GENETIC ALGORITHMS
 Definition of genetic
algorithm
• A genetic algorithm is a search heuristic that is
inspired by Charles Darwin’s theory of natural
evolution. This algorithm reflects the process of
natural selection where the fittest individuals are
selected for reproduction in order to produce offspring
of the next generation.
• Genetic Algorithm (GA) is a search-based
optimization technique based on the principles
of Genetics and Natural Selection. It is frequently
used to find optimal or near-optimal solutions to
difficult problems which otherwise would take a
lifetime to solve. It is frequently used to solve
optimization problems, in research, and in machine
learning.
 Applications of genetic algorithm
• Optimization − Genetic Algorithms are most commonly used in
optimization problems wherein we have to maximize or minimize
a given objective function value under a given set of constraints.
• Economics − GAs are also used to characterize various economic
models like the cobweb model, game theory equilibrium
resolution, asset pricing, etc.
• Neural Networks − GAs are also used to train neural networks,
particularly recurrent neural networks.
• Parallelization − GAs also have very good parallel capabilities,
and prove to be very effective means in solving certain problems,
and also provide a good area for research.
• Image Processing − GAs are used for various digital image
processing (DIP) tasks as well like dense pixel matching.
 Scheduling applications − GAs
Vehicle routing problems −
are used to solve various
With multiple soft time windows,
scheduling problems as well,
multiple depots and a
particularly the time tabling
heterogeneous fleet.
problem.

Robot Trajectory Generation − Parametric Design of Aircraft −

GAs have been used to plan the GAs have been used to design
path which a robot arm takes by aircrafts by varying the
moving from one point to parameters and evolving better
another. solutions.
• DNA Analysis − GAs have been used to
determine the structure of DNA using
spectrometric data about the sample.

• Multimodal Optimization − GAs are

obviously very good approaches for multimodal
optimization in which we have  to find multiple
optimum solutions.

• Traveling salesman problem and its

applications − GAs have been used to solve the
TSP, which is a well-known combinatorial
problem using novel crossover and packing
strategies.