TOPIC-:MAJOR AREAS OF

SOFT COMPUTING

NAME ROHIT
CLASS -:MCA(3RD SEMESTER)
ROLL NO-:2111930
SUBJECT-: ARTIFICIAL INTELLIGENCE
& SOFT COMPUTING
SOFT COMPUTING

 Soft computing is the process of solving real-life

complex problems using approximate calculations
and gives solutions that are not very specific in
nature just like the human brain works, which,
unlike traditional computing, focuses on impartial
truths and approximates.
The major areas of soft
computing are:
 Fuzzy Logic (FL)
 Evolutionary Computation (EC)
 Machine Learning (ML)
 Probabilistic Reasoning (PR)
1. FUZZY LOGIC(FL)
 Fuzzy logic is applied with great success in various control application. Almost all
the consumer products have fuzzy control. Some of the examples include controlling
your room temperature with the help of air-conditioner, anti-braking system used in
vehicles, control on traffic lights, washing machines, large economic systems, etc
 A control system is an arrangement of physical components designed to alter
another physical system so that this system exhibits certain desired characteristics.
 While applying traditional control, one needs to know about the model and the
objective function formulated in precise terms. This makes it very difficult to apply
in many cases.
 By applying fuzzy logic for control we can utilize the human expertise and
experience for designing a controller.
 The fuzzy control rules, basically the IF-THEN rules, can be best utilized in
designing a controller.
Architecture of Fuzzy LogicControl-:
Major Components of FLC-:
 Followings are the major components of the FLC as shown in the
above figure
 Fuzzifier − The role of fuzzifier is to convert the crisp input values into fuzzy values.

 Fuzzy Knowledge Base − It stores the knowledge about all the input-output fuzzy relationships. It also
has the membership function which defines the input variables to the fuzzy rule base and the output
variables to the plant under control.

 Fuzzy Rule Base − It stores the knowledge about the operation of the process of domain.

 Inference Engine − It acts as a kernel of any FLC. Basically it simulates human decisions by performing
approximate reasoning.

 Defuzzifier − The role of defuzzifier is to convert the fuzzy values into crisp values getting from fuzzy
inference engine.
Advantages of Fuzzy Logic Control-:
 Cheaper − Developing a FLC is comparatively cheaper than developing model
based or other controller in terms of performance.
 Robust − FLCs are more robust than PID controllers because of their
capability to cover a huge range of operating conditions.
 Customizable − FLCs are customizable.
 Emulate human deductive thinking − Basically FLC is designed to emulate
human deductive thinking, the process people use to infer conclusion from
what they know.
 Reliability − FLC is more reliable than conventional control system.
 Efficiency − Fuzzy logic provides more efficiency when applied in control
system.
Disadvantages of Fuzzy Logic Control-:

 Requires lots of data − FLC needs lots of data to be

applied.
 Useful in case of moderate historical data − FLC is not
useful for programs much smaller or larger than historical
data.
 Needs high human expertise − This is one drawback as
the accuracy of the system depends on the knowledge and
expertise of human beings.
 Needs regular updating of rules − The rules must be
updated with time.
MACHINE LEARNING(ML)-:
 Machine Learning is the field of study that gives
computers the capability to learn without being explicitly
programmed. ML is one of the most exciting technologies
that one would have ever come across. As it is evident
from the name, it gives the computer that makes it more
similar to humans: The ability to learn. Machine learning
is actively being used today, perhaps in many more places
than one would expect.
Applications of Machine Learning :-
 Web Search Engine: One of the reasons why search engines like
google, bing etc work so well is because the system has learnt how to
rank pages through a complex learning algorithm.
 Photo tagging Applications: Be it facebook or any other photo
tagging application, the ability to tag friends makes it even more
happening. It is all possible because of a face recognition algorithm
that runs behind the application.
 Spam Detector: Our mail agent like Gmail or Hotmail does a lot of
hard work for us in classifying the mails and moving the spam mails to
spam folder. This is again achieved by a spam classifier running in the
back end of mail application.
EXAMPLES OF MACHINE LEARNING-:
 Database Mining for growth of automation: Typical applications include Web-click
data for better UX( User eXperience), Medical records for better automation in
healthcare, biological data and many more.
 Applications that cannot be programmed: There are some tasks that cannot be
programmed as the computers we use are not modelled that way. Examples include
Autonomous Driving, Recognition tasks from unordered data (Face Recognition/
Handwriting Recognition), Natural language Processing, computer Vision etc.
 Understanding Human Learning: This is the closest we have understood and mimicked
the human brain. It is the start of a new revolution, The real AI. Now, After a brief
insight lets come to a more formal definition of Machine Learning
 Arthur Samuel(1959): “Machine Learning is a field of study that gives computers, the
ability to learn without explicitly being programmed.”Samuel wrote a Checker playing
program which could learn over time. At first it could be easily won. But over time, it
learnt all the board position that would eventually lead him to victory or loss and thus
became a better chess player than Samuel itself. This was one of the most early
attempts of defining Machine Learning and is somewhat less formal.
 Tom Michel(1999): “A computer program is said to learn from experience E with
respect to some class of tasks T and performance measure P, if its performance at tasks
in T, as measured by P, improves with experience E.” This is a more formal and
mathematical definition. For the previous Chess program
Evolutionary Computation (EC)
 Evolutionary computation is a sub-field of artificial intelligence (AI)
and is used extensively in complex optimization problems and for
continuous optimization. Evolutionary computation is used to solve
problems that have too many variables for traditional algorithms.
Computers performing evolutionary computing run such evolutionary
algorithms as genetic algorithms, evolutionary programming, genetic
programming and swarm intelligence models like ant colony
optimization or particle swarm optimization. 
 The computational models using evolutionary algorithms apply
evolutionary processes in order to solve complex problems. These
evolutionary processes are inspired by biological evolution theory.
Evolving algorithms use principles such as inheritance from previous
successful generations, and natural selection where the best solutions
pass their traits on to the successive generations.
History of Evolutionary Computation-:
 L. Fogel 1962 (San Diego, CA):
Evolutionary Programming
 J. Holland 1962 (Ann Arbor, MI):
Genetic Algorithms
 I. Rechenberg & H.-P. Schwefel 1965 (Berlin,
Germany): Evolution Strategies
 J. Koza 1989 (Palo Alto, CA):
Genetic Programming
Components of Evolutionary
Computing-:
 Genetic Algorithms –
Invented by John Holland (University of Michigan)
in the 1960’s
 Evolution Strategies –
Invented by Ingo Rechenberg (Technical University
Berlin) in the 1960’s
 Started out as individual developments, but have begun
to converge in the last few years
How evolutionary computation
works-:
 An initial batch of possible solutions is created with the
start of an evolutionary computation. The solutions once
tried are refined as weaker solutions are stochastically
removed and small random changes are introduced to
successive generations. As the generations pass the
solutions become increasingly refined. In the end the
solutions produced by evolutionary computation can be
tightly optimized, even though in the beginning, the
approach is not understood.
The Applications of Evolutionary
Computation are-:
 Solving Optimization Problems
 Designing Robots
 Creating Decision Trees
 Tuning Data Mining Algorithms
 Training Neural Networks
 Tuning Hyperparameters
Probabilistic Reasoning (PR)-:
 Probabilistic reasoning is a form of knowledge
representation in which the concept of probability is used
to indicate the degree of uncertainty in knowledge. In AI,
probabilistic models are used to examine data using
statistical codes. It was one of the first machine learning
methods. To this day, it's still widely used. The Naive
Bayes algorithm is one of the most well-known algorithms
in t
 In Artificial Intelligence and Cognitive Science,
probabilistic approaches are critical for generating,
reasoning, and making decisions (simple and
complex).his group.
How does it work-:
 Probabilistic modelling provides a framework for accepting the
concept of learning. The probabilistic framework specifies how to
express and deploy model reservations. In scientific data analysis,
predictions play a significant role. Machine learning, automation,
cognitive computing, and artificial intelligence all rely heavily on
them.

AI makes use of probabilistic reasoning:

 When we are uncertain about the premises

 When the number of possible predicates becomes unmanageable

 When it is known that an experiment contains an error

Causes of Uncertainty -:
Following are some leading causes of uncertainty to occur in the real
world.

 Information occurred from unreliable sources.

 Experimental Errors

 Equipment fault

 Temperature variation

 Climate change.
THANK
YOU