Question Bank
Add a question- What are the limitations of Hopfield network? Suggest methods that may overcome these limitations.
- Describe how a feed forward multi layer neural network may be trained for a function approximation task. Illustrate with an example.
- 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.
- Explain in detail about the Multi layer artificial neural network with neat diagram.
- Explain in detail about the single layer artificial neural network with diagram.
- Describe how a neural network may be trained for a pattern recognition task. Illustrate with an example
- Discuss in detail about orienting subsystem in an ART network.
- What are the advantages of ART network. Discuss about gain control in ART network.
- Explain the various applications of counter propagation.
- Explain briefly about the counter propagation-training algorithm.
- Explain the Kohonen’s learning algorithm.
- What is the Kohonen layer architure and explain its features.
- The truncated energy function, E(v), of a certain two-neuron network is specified as ,Assuming high-gain neurons, (a) find the weight matrix W and the bias current vector i. (b) Determine whether single-layer feedback neural network postulates (symmetry and lack of self-feedback) are fulfilled for W and i computed in part (a).
- Explain about the generalized delta- rule and derive the weight updatation for a multi layer feed forward neural network.
- State and prove the perceptron convergence theorem.
- What is the delta learning rule in neural networks? Explain with the help of an Illustration.
- What is the Hebbian-learning rule for training neural networks? Explain with the help of an illustration.
- Describe how a neural network may be trained for a pattern recognition task. Illustrate with an example
- Give a detailed note on (b) ART2 simulation.
- Give a detailed note on (a) ART1 data structures.
- Derive expressions for the weight updation involved in counter propagation.
- Discuss how the “Winner-Take-All” in the Kohonen’s layer is implemented and explain the architecture, Also explain the training algorithm.
- Construct an energy function for a discrete Hopfield neural network of size N×N neurons. Show that the energy function decreases every time the neuron output is changed.
- Explain about the generalized delta- rule and derive the weight updatation for a multi layer feed forward neural network.
- Explain the use of ANNs for clustering and feature detection.
- Briefly discuss about linear separability and the solution for EX-OR problem.Also suggest a network that can solve EX-OR problem.
- Give a brief description of neural networks as optimizing networks.