Biological-Type Neural Networks

It is estimated that the human brain contains over 100 billion () neurons and  synapses in the human nervous system. Studies of brain anatomy of the neurons indicate more than 1000 synapses on the input and output of each neuron. Note that, although the neuron's switch time (a few miliseconds) is about a millionfold times slower than current computer elements, they have a thousandfold greater connectivity than today's supercomputers.

The main objective of biological-type neural nets is to develope a synthetic element for verifying hypotheses concerning biological systems.

Neurons and the interconnections synapses constitute the key elements for neural information processing. See this figure.

Most neurons possess tree-like structures called dendrites wich receive income signals from other neurons across junction called synapses. Some neurons communicate with only a few nerby ones, whereas others make contact with thousands.

There are three parts in a neuron:

  1. a neuron cell body,
  2. branching extensions called dendrites for receiving input, and
  3. an axon that carries the neuron's output to the dendrites of other neurons.
How two or more neurons interact is not already well known, is different for different neurons. Generally speaking, a neuron sends its output to other neurons via its axon. An axon carries information through a series of action potentials, or waves of current, that depends on the neuron's potential. This process is often modeled as a propagation rule represented by a net value u(.).

A neuron collects signals at its synapses by summing all the excitatory and inhibitory influences acting on it. If the excitatory influences are dominant, then the neuron fires and sends this message to other neurons via the outgoing synapses. In this sense, the neuron function can be modeled as a simple threshold function f(.). As shown in the following figure the neuron fires if the combined signal strength exceeds a certain threshold, in the general case the neuron value is given by an activation function f(.).

Application-Driven Neural Networks

Contents

Artificial Neural Networks
About this Tutorial