Competitive learning

Competitive Learning
One question which seems to puzzle many of those who encounter unsupervised learning for the first time is how can anything useful be achieved when input information is simply poured into a black box with no provision of any ...

Competitive learning rules- here the output neurons of an ANN compete among themselves to become activated or fired, with the result that only one output neuron, or one neuron per group, is on at one time.

Simple Competitive Learning
In competitive networks, output units compete for the right to respond.
Goal: method of clustering - divide the data into a number of clusters such that the inputs in the same cluster are in some sense similar.

^ Competitive learning, Hebbian coincidence learning, Hopfield networks and attractor networks:
^ Lisp:
Luger & Stubblefield 2004, pp. 723-821
Crevier 1993, pp. 59-62,
Russell & Norvig 2003, p. 18 ...

Prototyping came about through a data classification technique called competitive learning. Competition learning is employed throughout different fields in AI, especially in neural networks or more specificially self-organizing networks.

The Kohonen network (Kohonen, 1982, 1984) can be seen as an extension to the competitive learning network, although this is chronologically incorrect. Also, the Kohonen network has a diferent set of applications.

For example, after such a competitive learning process one hidden layer node might respond to ellipses of a certain size, ...

4 Competitive Learning 474
11.5 Hebbian Coincidence Learning 484
11.6 Attractor Networks or "Memories" 495
11.7 Epilogue and References 505
11.8 Exercises 506
12 MACHINE LEARNING: GENETIC AND EMERGENT 507
12.

See also: Neural network, Classification, Artificial neural networks, Artificial neural network, Perceptron