1. What Are Anns? What Are Their Characteristics, Applications, Advantages

UNIT-I 1. What

are

ANNs?

What

are

their

characteristics,

applications,

advantages of ANN? 2. Explain briefly about the biological neuron? Define an Artificial Neuron and gives its functionality? 3. What is Activation function? Describe various types of Activation functions? 4. Explain Feed forward & recurrent networks and distinguish between

them? 1.Explain in detail about the single layer ANN with diagram. Explain in detail about the Multi layer ANN with neat diagram. 2. What is the Hebbian learning rule for training NN & what is the delta

learning rule in NN? Explain with the help of an illustration? 3. Explain about the generalized delta rule and derive the weight

updatation for a multi layer feed forward NN. 4.Describe how a feed forward multi layer NN may be trained for a function approximation task. Illustrate with an example.

UNIT-II 1. Briefly discuss about linear separability and the solution for EX_OR problem. Also suggest a network that can solve EX-OR problem. 2. Implement a back propagation algorithm to solve Ex-OR problem and

try the architecture in which there is a hidden layer with three hidden units and the network is fully connected? 3. Explain briefly about the counter propagation training algorithm. Explain the various applications of counter propagation. 4. Explain the operation of counter propagation with suitable network

model and give the equations for training. 5. State and prove the perceptron convergence theorem? 6. Derive expressions for the weight updating involved in counter propagation.

7. Compare the similarities and differences between single layer and

multi layer

perceptrons and also discuss in what aspects multi

layer perceptrons are advantageous over single layer perceptrons?

UNIT-III 1. Explain the Kohonen’s method of unsupervised learning. Discuss any

example as its application. What are the applications of Kohonen? 2. Explain the weight training of the Kohonen Layer? 3. Write in detail about the training of the Grossberg layer? 4. What are Self organizing networks? Explain Kohonen’s self organizing

Networks? 1. Discuss how the “winner take all” in the Kohonen’s layer is implemented and explain the architecture, also explain the training algorithm. 2. What is the Kohonen layer architecture and explain its features. Explain the Kohonen’s learning algorithm.

UNIT-IV 1. What is the Hopfield network? Describe how it can be used to have analog to digital conversion? 2. Show how the travelling salesman problem can be solved using

Hopfield networks Or

Discuss how the traveling salesman problem

can be solved using the Hopfield model. 3. Explain in detail about the Boltzmann machine along with its applications. 4. What

are

Associative

memories?

Differentiate

between

Auto

associative and heteo-associative memories. 5. Write in detail about Bidirectional Associative Memories (BAMs). Also give their applications. 6. Discuss in detail about the different kinds of BAMs. 1. Construct an energy function for a discrete Hopfield NN of size NxN neurons. Show that the energy function decreases every time the neuron output is changed.

2. What are the limitations of Hopfield Network? Suggest methods that may overcome these limitations? 3. What are the modes of operation of a Hopfield network? Explain the algorithm for storage of information in a Hopfield network. Similarly explain the recall algorithm.