Marathwada Shikshan Prasarak Mandal’s
Deogiri Institute of Engineering and Management Studies, Aurangabad
Department of Computer Science and Engineering
Paper Solution SC Nov/Dec 2017
Class : BE CSE _
__________________________________________________________________________
Q. 1
Answer the following.
1)
Define Soft Computing? Differentiate between soft computing and hard computing.
Ans:
It is the composition of methodologies designed to model and enable solution to real world problems. Soft
Computing aims to exploit the tolerance for imprecision, uncertainty, approximate reasoning, and partial truth in
order to achieve close resemblance with human decisions.
Soft Computing vs Hard Computing:
1. Soft Computing is tolerant
of imprecision, uncertainty, partial truth and approximation whereas
Hard
Computing requires a precisely state analytic model.
2. Soft Computing is based on
fuzzy logic
, neural sets, and probabilistic reasoning whereas Hard Computing is
based on binary logic, crisp system, numerical analysis and crisp software.
3. Soft computing has the characteristics of approximation and dispositionality whereas Hard computing has the
characteristics of precision and categoricity.
4.
Soft computing can evolve its own programs whereas Hard computing requires programs to be written.
5. Soft computing can use multivalued or fuzzy logic whereas Hard computing uses twovalued logic.
6. Soft computing incorporates stochasticity whereas Hard computing is deterministic.
7.
Soft computing can deal with ambiguous and noisy data whereas Hard computing requires exact input data.
8. Soft computing allows parallel computations whereas Hard computing is strictly sequential.
9. Soft computing can yield approximate answers whereas Hard computing produces precise answers.
2) What is linearly seperable and linearly nonseperable problems? Explain it with example.
Ans:Consider twoinput patterns
being classified into two classes as shown in figure
2.9
. Each
point with either symbol of
or
represents a pattern with a set of values
. Each pattern is
classified into one of two classes. Notice that these classes can be separated with a single line
. They are
known as
linearly separable
patterns.
Linear separability
refers to the fact that classes of patterns with

dimensional vector
can be separated with a single
decision surface
. In the case
above, the line
represents the decision surface.
The processing unit of a singlelayer perceptron network is able to categorize a set of patterns into two classes
as the linear threshold function defines their linear separability. Conversely, the two classes
must
be linearly
separable in order for the perceptron network to function correctly [
Hay99
]. Indeed, this is the main limitation
of a singlelayer perceptron network.
The most classic example of linearly inseparable pattern is a logical exclusiveOR (XOR) function. Shown in
figure
2.10
is the illustration of XOR function that two classes, 0 for black dot and 1 for white dot, cannot be
separated with a single line. The solution seems that patterns of
can be logically classified with
two lines
and
[
BJ91
].
You've reached the end of your free preview.
Want to read all 21 pages?
 Spring '16
 213
 Machine Learning, Artificial neural network, neural network, Selforganizing map