Scribd
Upload
5K views

Soft Computing Unit 1 and 2 Questions

This document contains 35 questions related to the topics covered in the first two units of Soft Computing: Unit I introduces soft computing and defines it as a way of computing that is tolerant of imprecision, uncertainty, and partial truth. It contrasts soft computing with hard computing and discusses expert systems and their applications. Unit II focuses on artificial neural networks (ANN). It defines ANN and compares biological neural networks to artificial ones. It discusses basic ANN models including perceptrons, adaptive linear neurons (Adaline), multiple adaptive linear neurons (Madaline), and backpropagation networks. It covers ANN learning methods such as supervised, unsupervised, and reinforcement learning and presents algorithms for training various neural network models. The

Uploaded by

Harshali Y. Patil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
5K views

Soft Computing Unit 1 and 2 Questions

This document contains 35 questions related to the topics covered in the first two units of Soft Computing: Unit I introduces soft computing and defines it as a way of computing that is tolerant of imprecision, uncertainty, and partial truth. It contrasts soft computing with hard computing and discusses expert systems and their applications. Unit II focuses on artificial neural networks (ANN). It defines ANN and compares biological neural networks to artificial ones. It discusses basic ANN models including perceptrons, adaptive linear neurons (Adaline), multiple adaptive linear neurons (Madaline), and backpropagation networks. It covers ANN learning methods such as supervised, unsupervised, and reinforcement learning and presents algorithms for training various neural network models. The

Uploaded by

Harshali Y. Patil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Q.

1
Q.2
Q.3
Q.4
Q.5

Q.1
Q.2
Q.3
Q.4
Q.5

Q.6
Q.7
Q.8
Q.9
Q.10
Q.11
Q.12
Q.13
Q.14
Q.15
Q.16
Q.17
Q.18
Q.19
Q.20
Q.21

UNIT-I (Introduction to Soft Computing)


What is Soft Computing?
Differentiate between Hard Computing and Soft Computing.
What is an expert system? Explain in brief components of expert system. What
are the applications of expert system?
Explain in brief application areas of Soft computing?
List the applications of Soft computing.
UNIT-II (ANN)
What is ANN? List the characteristics of ANN.
Compare biological neural network and Artificial neural network.
Explain in brief basic models of Artificial Neural Network.
What is learning? What are different types of learning?
Write a short note on
1) Supervised learning
2) Unsupervised learning
3) Reinforcement learning
4) Activation function
5) Perceptron network
6) Adaptive Linear Neuron (Adaline)
7) Multiple Adaptive Linear Neuron (Madaline)
What is supervised learning and how it is different from unsupervised learning?
What is the building block of the perceptron? Does perceptron require
supervised learning? If no, What does it require?
List the limitations of perceptron and applications of perceptron network.
List the stages involved in training of back propagation network.
What is local minima and global minima?
Write an algorithm for training perceptron network.
Write an algorithm for training Adaptive Linear Neuron (Adaline)
Write an algorithm for training Multiple Adaptive Linear Neuron (Madaline)
What do you understand by back propagation network? Explain in brief its
architecture.
Explain in brief error back propagation algorithm.
What are the applications of BPN?
What are the factors that improve the convergence of learning in BPN
network?
What is the necessity of momentum factor in weight updation process?
What is content addressable memory?
What is the functional difference between a RAM and a CAM
Explain the Hebb rule training algorithm used in pattern association
1

SOFT COMPUTING QUESTION BANK

Q.22
Q.23
Q.24
Q.25

List the fixed weight competitive nets. Explain one in brief.


List the special neural networks for typical applications.
What is the principle behind simulated annealing network? Explain SAN in brief.
For the network shown in figure, calculate the net input to the output neuron

Q.26 Calculate the net input for the network shown in figure with bias included in
the network

Q.27 Obtain the output of the neuron Y for the network shown in figure using
activation functions as:
(i)
binary sigmoidal and (ii) bipolar sigmoidal

Q.28 Construct a Maxnet with four neurons and inhibitory weight =0.2, given the
initial activations (input signals) as follows:
A1(0)=0.3 , A2(0)=0.5 , A3(0)=0.7, A4(0)=0.9
Q.29 Construct a Maxnet with four neurons and inhibitory weight =0.3, given the
initial
al activations (input signals) as follows:
2

SOFT COMPUTING QUESTION BANK

Q.30
Q.31
Q.32
Q.33
Q.34

A1(0)=0.4, A2(0)=0.5, A3(0)=0.6, A4(0)=0.8


Implement AND function using perceptron networks for bipolar inputs and
targets.
Implement OR function using perceptron networks for bipolar inputs and
targets.
Implement ANDNOT function when all the inputs are presented only one time.
Use bipolar inputs and targets.
Implement OR function with bipolar inputs and targets using Adaline network.
Using Madaline network, implement XOR functio
function
n with bipolar inputs and
targets. Assume the required parameters for training of the network

Q.35 Using back-propagation


propagation network, find the new weights for the net shown in
figure. It is presented with the input pattern [0,1] and the target output is 1.
Use a learning rate =0.25 and binary sigmoidal activation function

SOFT COMPUTING QUESTION BANK

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy