Assignment No.

Unit 1. Soft Computing Basics

1. What is soft computing?

Soft computing is a collection of artificial intelligence (AI)

computing techniques that gives devices human-like problem-
solving capabilities. It includes the basics of neural networks,
fuzzy logic, and genetic algorithms.

The soft computing theory and techniques were introduced in the

1980s. And the term was coined by Lofti A. Zadeh, a
mathematician, computer scientist, electrical engineer, AI
researcher, and professor emeritus of computer science at the
University of California, Berkeley.
 2. Explain soft computing vs hard computing.

Soft Hard
S.NO Computing Computing

Hard computing
Soft computing has has the features of
the features of exactitude
approximation and (precision) and
1. dispositionality. categoricity.

Hard computing is
Soft computing is deterministic in
2. stochastic in nature. nature.

Soft computing Hard computing

works on ambiguous works on exact
3. and noisy data. data.

Soft computing can Hard computing

perform parallel performs sequential
4. computations. computations.

Soft computing Hard computing

produces produces precise
5. approximate results. results.
 3. Give short note on-

● Neural Network
Neural networks are artificial systems that were inspired by biological neural
networks. These systems learn to perform tasks by being exposed to various
datasets and examples without any task-specific rules. The idea is that the system
generates identifying characteristics from the data they have been passed without
being programmed with a pre-programmed understanding of these datasets.
Neural networks are based on computational models for threshold logic. Threshold
logic is a combination of algorithms and mathematics. Neural networks are based
either on the study of the brain or on the application of neural networks to artificial
intelligence. The work has led to improvements in finite automata theory.

● Fuzzy Logic
The term fuzzy refers to things that are not clear or are vague. In the real world
many times we encounter a situation when we can’t determine whether the state is
true or false, their fuzzy logic provides very valuable flexibility for reasoning. In
this way, we can consider the inaccuracies and uncertainties of any situation. 
In the Boolean system truth value, 1.0 represents the absolute truth value and 0.0
represents the absolute false value. But in the fuzzy system, there is no logic for the
absolute truth and absolute false value. But in fuzzy logic, there is an intermediate
value too present which is partially true and partially false. 

● Genetic Algorithm

Genetic Algorithms (GAs) are adaptive heuristic search algorithms that belong to
the larger part of evolutionary algorithms. Genetic algorithms are based on the
ideas of natural selection and genetics. These are intelligent exploitation of random
search provided with historical data to direct the search into the region of better
performance in solution space. They are commonly used to generate high-
quality solutions for optimization problems and search problems.
 ● Hybrid systems

 A Hybrid system is an intelligent system that is framed by combining at least two

intelligent technologies like Fuzzy Logic, Neural networks, Genetic algorithms,
reinforcement learning, etc. The combination of different techniques in one
computational model makes these systems possess an extended range of
capabilities. These systems are capable of reasoning and learning in an uncertain
and imprecise environment. These systems can provide human-like expertise like
domain knowledge, adaptation in noisy environments, etc. 

4. Explain applications of soft computing.

Communication

Communication requires a very dynamic environment as the demand can occur

randomly, and most of the time, there is not much of a pattern to work with.

Soft computing uses an artificial neural network and fuzzy logic to determine when
there is a sudden surge in demand and accordingly allocates resources for that
particular node.

Home Appliances
This is a very interesting application since we are already using some of this.Our
everyday appliances such as refrigerators, microwaves, washing machines, etc. are
becoming smart because of artificial intelligence, machine learning, and fuzzy
logic.
Robotics
This is one of the very upcoming fields to use soft computing’s fuzzy logic and
expert systems techniques.
It helps manage industries efficiently in not only production but also inventory
management.

Some of the large e-commerce companies are already employing robots with soft
computing embedded to help manage the substantial load of goods that goes
through the warehouse on a daily basis.

Transportation
With connected cars, transportation is another major industry making use of soft
computing at its various stages.

Right from the production of cars in the factory to be on the road for navigation,
traffic prediction, troubleshooting, and diagnostics of the car, fuzzy logic and
evolutionary computing are widely used.

Similar solutions are also used in elevators when a single system is in charge of
handling multiple elevators.

Healthcare
No one would have guessed this as an application since it’s such a critical industry.

One wrong decision can result in loss of lives or permanent damage to the patients.

But soft computing, using a horde of its various logic has been found to be quite
accurate in terms of diagnosis and results.

Doctors are increasingly turning towards soft computing to diagnose the patients’
ailments from the symptoms accurately and hence save on money and side effects
from medications of the wrong diagnosis.

5. Write applications of neural network.

● Social Media
● Marketing and Sales
 ● Healthcare
● Personal Assistants
● Image compression
● Stock exchange prediction
● Handwriting Recognition

6. Write applications of fuzzy logic.

● Industrial sector
● Transportation
● Securities
● Pattern recognition and classification
● Aerospace
● Automotive
● Defense
 

7. Write applications of genetic algorithm.

● Recurrent neural network

● Mutation testing
● Code breaking
● Filtering and signal processing
● Learning fuzzy rule base
● Traffic and shipment routing

8. List applications of soft computing.

● Power system analysis

● Investment and training
● Decision support system
● Soft computing based architecture
● Automotive systems and manufacturing
● Image processing and data compression

9. What is neural network architecture? Give its types

and explain them.
 An Artificial Neural Network (ANN) is an information processing paradigm
that is inspired by the brain. ANNs, like people, learn by examples. An ANN
is configured for a specific application, such as pattern recognition or data
classification, through a learning process. Learning largely involves
adjustments to the synaptic connections that exist between the neurons. 

There exist five basic types of neuron connection architecture: 

 
1. Single-layer feed-forward network
2. Multilayer feed-forward network
3. Single node with its own feedback
4. Single-layer recurrent network
5. Multilayer recurrent network

1. Single-layer feed forward network

In this type of network, we have only two layers input layer and output
layer but the input layer does not count because no computation is
performed in this layer. The output layer is formed when different
weights are applied on input nodes and the cumulative effect per node is
taken. After this, the neurons collectively give the output layer to
compute the output signals.
2. Multilayer feed forward network

This layer also has a hidden layer that is internal to the network and has
no direct contact with the external layer. The existence of one or more
hidden layers enables the network to be computationally stronger, feed-
forward network because of information? owes through the input
function, and the intermediate computations used to define the output Z.
There are no feedback connections in which outputs of the model are fed
back into itself.

3. Single node with its own feedback 

 When outputs can be directed back as inputs to the same layer or
preceding layer nodes, then it results in feedback networks. Recurrent
networks are feedback networks with closed loops. The above figure
shows a single recurrent network having a single neuron with feedback to
itself.

4. Single-layer recurrent network

The above network is a single-layer network with a feedback connection

in which the processing element’s output can be directed back to itself or
to another processing element or both. A recurrent neural network is a
class of artificial neural networks where connections between nodes form
a directed graph along a sequence. This allows it to exhibit dynamic
temporal behavior for a time sequence.
5. Multilayer recurrent network

In this type of network, processing element output can be directed to the

processing element in the same layer and in the preceding layer forming a
multilayer recurrent network. They perform the same task for every
element of a sequence, with the output being dependent on the previous
computations. Inputs are not needed at each time step. The main feature
of a Recurrent Neural Network is its hidden state, which captures some
information about a sequence.

10. Explain the characteristics of neural network.

● Since an ANN has a very expressive hypothesis space, it is important to
choose the approximate network topology (simplistic, layered, and multi-
layered) for a given problem to avoid model over fitting.

● ANN can handle redundant features because the weights are autonomous
and automatically learned during the learning process. The weights fir
redundant features tend to be insignificant.

● Training an ANN is time consuming particularly when the numbers of

hidden layers are quite significantly large.

● ANN are quite sensitive to the perspective of noise in the training data.
One approach to address this issue is to use a validation set to determine
and eliminate generalization error. Another approach is to adjust the
weights by some percentages at each iteration.

Submitted by-
Name: Sarvesh Muttepwar
Class: BE (B)
Roll no: 21CEBEB11
College: SKNSITS