0% found this document useful (0 votes)
82 views21 pages

Competitive Networks

Competitive neural networks are unsupervised learning networks where neurons compete with each other. The winning neuron is the one whose weight vector most closely matches the input vector. Competitive networks have two components - the Hemming net calculates the similarity between input and weight vectors, and the Maxnet selects the neuron with the maximum similarity value. During training, the winning neuron's weight vector moves closer to the input vector, causing the weight vectors to converge to cluster centroids over time. When new inputs are presented, competitive networks classify them based on which cluster centroid they are closest to.

Uploaded by

Shame Bope
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
82 views21 pages

Competitive Networks

Competitive neural networks are unsupervised learning networks where neurons compete with each other. The winning neuron is the one whose weight vector most closely matches the input vector. Competitive networks have two components - the Hemming net calculates the similarity between input and weight vectors, and the Maxnet selects the neuron with the maximum similarity value. During training, the winning neuron's weight vector moves closer to the input vector, causing the weight vectors to converge to cluster centroids over time. When new inputs are presented, competitive networks classify them based on which cluster centroid they are closest to.

Uploaded by

Shame Bope
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 21

A model of Neural networks

COMPETITIVE NETWORKS
DEFINITION
Competitive networks are networks where neurons
compete with one another. The "winner" of each
training session is the neuron whose weight vector is
most similar to the input vector. It is a form of
unsupervised learning in artificial neural networks,
in which nodes compete for the right to respond to a
subset of the input data.
Competitive network diagram
COMPETITIVE NETWORKS
ARCHITECTURE
ARCHITECTURE EXPLANATION
• The ‖ dist ‖ box in this figure accepts the input vector p
and the input weight matrix IW1,1, and produces a vector
having S1 elements. The elements are the negative of the
distances between the input vector and vectors iIW1,1
formed from the rows of the input weight matrix.
• Compute the net input n1 of a competitive layer by finding
the negative distance between input vector p and the
weight vectors and adding the biases b. If all biases are
zero, the maximum net input a neuron can have is 0. This
occurs when the input vector p equals that neuron's
weight vector.
COMPOSITION
• competitive networks are composed of two networks:
the Hemming net and the Maxnet. Each of them
specializes in a different function:
• 1.
• The Hemming net measures how much the input
vector resembles the weight vector of each
perceptron.
• 2.
• The maxnet finds the perceptron with the maximum
value.
The Hemming net:

Each perceptron at the top layer of the Hemming net


calculates a weighted sum of the input values. This
weighted sum can be interpreted as the dot product
of the input vector and the weight vector.
The Hemming net:
The Maxnet
The maxnet is a fully connected network with each
node connecting to every other nodes, including
itself. The basic idea is that the nodes compete
against each other by sending out inhibiting signals to
each other.
This is done by setting the weights of the connections
between different nodes to be negative and applying
the following algorithm:
The Maxnet
MAXNET ALGORITHM
Putting them together:
Putting them together....

• In a simple competitive network, a Maxnet connects


the top nodes of the Hemming net. Whenever an
input is presented, the Hemming net finds out the
distance of the weight vector of each node from the
input vector via the dot product, while the Maxnet
selects the node with the greatest dot product. In this
way, the whole network selects the node with its
weight vector closest to the input vector, i.e. the
winner.
Putting them together.....
The network learns by moving the winning weight
vector towards the input vector:

while the other weight vectors remain unchanged.


Winner: move towards the input vector
Winner: move towards the input
vector.....
This process is repeated for all the samples for many
times. If the samples are in clusters, then every time
the winning weight vector should move towards a
particular sample in one of the clusters. Eventually
each of the weight vectors would converge to the
centroid of one cluster. At this point, the training is
complete.
weight vectors: centroids of
various clusters
weight vectors: centroids of
various clusters........
When new samples are presented to a trained net, it
is compared to the weight vectors which are the
centroids of each cluster. By measuring the distance
from the weight vectors using the Hemming net, the
sample would be correctly grouped into the cluster to
which it is closest.
Advantages
o Won’t result in excessive positive or negative weights
o Ideal when we have to analyze raw data of which we have no
prior knowledge.

o Can be used for Vector quantization.


o Can be used for clustering – competitive rule allows a single
Disadvantages
o If a weight vector is far away from any of the data clusters,
it may never win competition.
o You are not sure about what it has learnt.
o If used for clustering, number of clusters have to be
decided in advance.
o Inner product takes account of both direction and
magnitude of vector.
o If vectors are not normalized, may select wrong weight
vector after competition.
Applications
o
Analyze raw data
o Image browsing systems
o Medical diagnosis
o Speech recognition (this Kohonen used initially)
o Data compression
o Environmental modeling

You might also like