Scribd
Upload
25 views

Soft Computing: Unsupervised Networks

This document contains questions and answers about various unsupervised neural networks. It begins by defining unsupervised training as providing a sequence of input vectors without specifying target vectors, so the network modifies weights to assign similar inputs to the same output unit. It then asks questions about the architectures and activation/weight update equations of MAXNET, Mexican Hat, and Hamming networks. It discusses Hebbian learning and Adaptive Resonance Theory. It defines terms like stability-plasticity dilemma and leaky learning. It asks about Kohonen self-organizing maps and their applications. Finally, it asks to explain competitive learning networks, Kohonen self-organizing networks, learning vector quantization, binary Hopfield networks, and adaptive resonance theory networks

Uploaded by

Vinothsaravanan Ramakrishnan
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
25 views

Soft Computing: Unsupervised Networks

This document contains questions and answers about various unsupervised neural networks. It begins by defining unsupervised training as providing a sequence of input vectors without specifying target vectors, so the network modifies weights to assign similar inputs to the same output unit. It then asks questions about the architectures and activation/weight update equations of MAXNET, Mexican Hat, and Hamming networks. It discusses Hebbian learning and Adaptive Resonance Theory. It defines terms like stability-plasticity dilemma and leaky learning. It asks about Kohonen self-organizing maps and their applications. Finally, it asks to explain competitive learning networks, Kohonen self-organizing networks, learning vector quantization, binary Hopfield networks, and adaptive resonance theory networks

Uploaded by

Vinothsaravanan Ramakrishnan
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/ 2

S. L.

Varma

Soft Computing
SC: Question Banks on Unsupervised Networks

1. What is unsupervised training?


A sequence of input vector is provided, but no target vectors are specified. The net modifies the weights
so that the most similar input vectors are assigned to the same output unit.
2. Draw the architecture of MAXNET.
Draw the architecture.
3. What is the equation for updating the activation?
Aj(new)=f[aj(old) _ _ ak(old)]
3. Draw the architecture of Mexican cat.
Draw the architecture.
4. What is the activation unit xi at time t of Mexican cat?
Xi(t) = f[Si(t) + _ wk x i+k(t-1)]
5. What is hamming net? Define hamming distance between two vectors? Draw the architecture of
hamming bet.
A hamming net is a maximum likelihood classifier net that can be used to determine which of the
exemplar vector is most similar to an input vector.
It is the number of components in which vector differ.
Draw the architecture.
6. What is the concept of hebbian learning?
Hebb proposed that learning occurs by modification of the synapse strengths (weights) in a manner such
that if two interconnected neurons are both on at the same time, then the weights between these neurons
should be increased.
7. Draw the architecture of Adaptive Resonance Theory.
Draw the architecture.
8. What is Auto associative net (Content addressable nature)?
9. Define the following terms:
- Stability-plasticity dilemma
- Leaky learning?
-A learning agent should be plastic, or adaptive in reacting to changing
environments meanwhile it should be stable to preserve knowledge acquired previously.
-To update the weights of both the winning and losing units, but use a significantly
smaller learning rate for the losers; this is commonly referred to au leaky learning.
27. What is Kohonen Self-organising maps (Topology preserving maps)? What are the application of
Kohonen self-organizing network and competitive learning network.
-Neural phonetic type writer, to learn ballistic arm movements.
-Data compression in communication and image processing, graph partitioning and
word perception models.
Unsupervised Networks
1. Explain the Competitive learning network with an example
- Architecture, Algorithm, Example

S. L. Varma

2. Explain the Kohonen self organising network with an example


- Architecture, Algorithm, and Example
3. Explain the Learning vector quantization vector network with an example
- Architecture, Algorithm, and Example
4. Explain the Binary Hopfield network with an example
- Architecture, Algorithm, and Example
5. Explain the Adaptive resonance theory network with an example
- Architecture, Algorithm, and Example

You might also like