Jawaharlal Nehru Technological University Anantapur 2010-1st Sem B.Tech Code :R7411009 4 IV (R07) Regular s, ember/ember ARTIFICIAL NEURAL NETWORKS - Question Paper

Code :R7411009 4
IV B.Tech I semester (R07) Regular Examinations, November/December 2010
ARTIFICIAL NEURAL NETWORKS
(Electronics & Instrumentation Engineering)
Time: three hours Max Marks: 80
ans any 5 ques.
All ques. carry equal marks
1. (a) discuss supervised and unsupervised learning in detail with help of block diagrams.
(b) discuss single layer and multilayer feed forward net.
2. (a) explain memory based learning in detail.
(b) Write about Mc-Culloch-Pitt's neuron model and find the models for NAND gate.
3. (a) Develop a perceptron for the AND function with bipolar inputs and targets.
(b) Di®erentiate ranging from local minima and global minima.
4. Develop an adaline network for ANDNOT function with bipolar inputs and bipolar targets.
5. (a) State the training algorithm used for forward only CPN.
(b) discuss Winner-Take All learning.
6. discuss continuous and discrete Hop¯eld network architecture.
7. (a) When an ART net is set to have plasticity?
(b) Write short note on the basic architecture and operation of ART network.
(c) elaborate the 2 kinds of learning in the ART net?
8. discuss in detail traveling salesman issues using Hop¯eld networks.

Earning:   Approval pending.