You are on page 1of 12

METHODOLOGIES OF SOFT

COMPUTING

Priyanka Shivaji Aher

UNDER THE GUIDANCE OF


Mr. Pravin Pawar
WHAT IS SOFT COMPUTING

 Soft computing is the use of approximate calculations to


provide imprecise but usable solutions to complex
computational problems. The approach enables solutions for
problems that may be either unsolvable or just too time-
consuming to solve with current hardware.

 These types of problems are considered as real-life problems


where the human-like intelligence is required to solve it.

 The soft computing term is define by Dr Lotfi Zadeh,


according to him, soft computing is an approach which
imitates the human mind to reason and learns in an
environment of uncertainty and impression.
ADVANTAGES OF SOFT COMPUTING

 Models based on human reasoning


 Closer to human thinking
 Doesn’t need any difficult mathematical calculation
 It is a real time expert system
 Work in equation and condition
 Biological inspiration
METHODOLOGIES OF SOFT
COMPUTING

1. Fuzzy Logic
2. Artificial Neural Networks
3. Genetic Algorithms And Evolutionary
Techniques
FUZZY LOGIC
 Fuzzy logic began with the 1965 proposal of fuzzy set theory
by Lotfi Zadeh Fuzzy logic has been applied to many fields,
from control theory to artificial intelligence
 Fuzzy logic deals with the decision making and control system
problems which cannot be converted into hard mathematical
formulae.
 Fuzzy logic has been extended to handle the concept of partial
truth, where the truth value may range between completely true
and completely false. Furthermore, when linguistic variables
are used, these degrees may be manages by specific function.
 This basically maps the inputs to the outputs logically in a
nonlinear manner, the way humans does it. Fuzzy logic is used
in automobile subsystem, air conditioners, cameras, etcetera.
BENEFITS IF FUZZY LOGIC

 Understand physical System and control requirements


 Develop a Linear Model of Plant Sensors and Actuators
 Determine a simplified Controller from Control Theory.
 Develop an algorithm for the controller
 Simulate, Debug and Implement Design.
Artificial Neural Networks

 Artificial Neural Networks is a modeling technique


inspired by the human nervous system that allows
learning by example from representative data that
describes a physical phenomenon or a decision process.
 The relationships between independent and dependent
variables can be established without assumptions about
any mathematical representation of the phenomena.
 Artificial neural networks perform classification, data
mining and prediction process and easily manage the
noisy input data by categorizing it into the groups or
mapping to an expected output.
BENEFITS OF ARTIFICIAL NEURAL
NETWORK

1. ORGANIC LEARNING
Neural networks can learn organically. This means an artificial neural
network’s outputs aren't limited entirely by inputs and results given to
them initially by an expert system. Artificial neural networks have the
ability to generalize their inputs.
2. NONLINEAR DATA PROCESSING
Nonlinear systems have the capability of finding shortcuts to reach
computationally expensive solutions. These systems can also infer connections
between data points, rather than waiting for records in a data source to be
explicitly linked. This nonlinear short-cut mechanism is fed into artificial
neural networking, which makes it valuable in commercial big-data analysis
3. FAULT TOLERANCE
Artificial neural networks have the potential for high fault
tolerance. When these networks are scaled across multiple
machines and multiple servers, they are able to route around
missing data or servers and nodes that can't communicate.
4. SELF-REPAIR
Artificial neural networks can do more than routing around
parts of the network that no longer operate. If they are asked for
finding out specific data that is no longer communicating, these
artificial neural networks can regenerate large amounts of data by
inference and help in determining the node that is not working.
Genetic Algorithms And Evolutionary
Techniques
 The genetic algorithm is one of the oldest and most known
optimization techniques, which are based on nature. In the
Genetic algorithms, the search for solution space imitates the
natural process which takes place in the environment, and the
Darwinian theory of species evolution is taken into
consideration.
 We present the main properties of each algorithm described
in this paper. We also show many state-of-the-art practical
applications and modifications of the early evolutionary
methods. 
 We present the following algorithms: genetic algorithms,
genetic programming, differential evolution, evolution
strategies, and evolutionary programming.
Benefits Of Genetic Algorithms And
Evolutionary Techniques
• Easy to understand
• Support multi-objective optimization
• Less time required for special applications
• Genetic Algorithm are intrinsically
• Inherently parallel & easily distributed
Conclusion
 The objective of soft Computing approaches is to realize a
new approach for analyzing and create flexible information
processing of humans such as sensing, understanding,
learning, recognizing and thinking.
 Fuzzy logic provides an alternative way to represent
linguistic and subjective attributes of the real world in
Computing
 The ANN simulates physiological features of the human
brain, and has been applied for non-linear mapping  by
numerical approach. 
 The GA simulates evolution on computer, and has been
applied for solving combinatorial optimization problems .  

You might also like