SRM University 2007 B.Tech Computer Science and Engineering BANK of ARTIFICIAL NEURAL NETWORKS - Question Paper

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
S.R.M INSTITUTE OF SCIENCE AND TECHNOLOGY

SUBJECT : ARTIFICIAL NEURAL NETWORKS
SUB.CODE : CS306
CLASS : III YEAR CSE
ques. BANK

UNIT-1
PART-A
1. Define ANN and Neural computing.
2. Distinguish ranging from Supervised and Unsupervised Learning.
3. Draw the basic topologies for (a) Nonrecurrent and (b) Recurrent Networks and distinguish ranging from them.
4. Give a few examples for Nonrecurrent and Recurrent ANNs. Specify the learning legal regulations used by every ANN.
5. Define Adaptive System and Generalization.
6. Mention the characteristics of issues suitable for ANNs.
7. List a few applications of ANNs.
8. What are the design parameters of ANN?
9. Explain the 3 classifications of ANNs based on their functions. discuss them in brief.
10. Define Learning and Learning legal regulations.
11. Distinguish ranging from Learning and Training.
12. How can you measure the likeness of 2 trends in the input space?
13. A 2 layer network is to have 4 inputs and 6 outputs. The range of the outputs is to be continuous ranging from 0 and 1. What can you tall about the network architecture? Specifically,
(a) How many neurons are needed in every layer?
(b) elaborate the dimensions of the first-layer and 2nd layer weight
matrices? (Hidden layer neurons are 5)
(c) What types of transfer functions can be used in every layer?
14. Mention the linear and nonlinear activation functions used in Artificial Neural Networks.
UNIT-I
PART-B
1. Write the differences ranging from conventional computers and ANN.
2. Explain in Detail how weights are adjusted in the various kinds of Learning legal regulations.(Both supervised and Unsupervised)
3. Write short notes on the subsequent.
a. Learning Rate Parameter
b. Momentum
c. Stability
d. Convergence
e. Generalization
4. (a) Write the advantages and disadvantages of Artificial Neural Networks.
(b) elaborate the design steps to be followed for using ANN for your problem?
5. (a) elaborate the relevant computational properties of the Human Brain?
(b) Write short notes on neural approaches to calculation.

UNIT-II
PART-A
1. Compare physical neuron and artificial neuron
2. What is called weight or connection strength?
3. Draw the model of a single artificial neuron and derive its output.
4. Draw the model of MP(McCulloch Pitts) neuron and state its characteristics.
5. What are the 2 approaches to add a bias input?
6. Distinguish ranging from linearly separable and nonlinearly separable issues. provide examples.
7. Define Perceptron convergence theorem.
8. What is XOR problem?
9. What is perceptron? Write the differences ranging from Single Layer Perceptron(SLP) and Multilayer Perceptron(MLP).

Earning:   Approval pending.