C++ Neural Networks and Fuzzy Logic: Preface

Lateral Inhibition

Lateral inhibition is a process that takes place in some biological neural networks. Lateral connections of

neurons in a given layer are formed, and squash distant neighbors. The strength of connections is inversely

related to distance. The positive, supportive connections are termed as excitatory while the negative,

squashing connections are termed inhibitory.

A biological example of lateral inhibition occurs in the human vision system.

The Mexican Hat Function

Figure 11.1 shows a function, called the mexican hat function, which shows the relationship between the

connection strength and the distance from the winning neuron. The effect of this function is to set up a

competitive environment for learning. Only winning neurons and their neighbors participate in learning for a

given input pattern.

Figure 11.1

  The mexican hat function showing lateral inhibition.