Figure 2 shows a representation of a biological neuron (A), artificial neuron
(B) and the architecture of artificial neural networks (C).
Japkowicz explains how an artificial neural network works: Information gets transmitted from artificial neuron
to artificial neuron
through highly parallel connections that get stronger and stronger as similar patterns are observed.
. While originally based on a simplistic model of the
In an artificial neuron
, the information enters the body of an artificial neuron
via inputs that are individually weighed.
The basic building block of every artificial neural network is an artificial neuron
, that is, a simple mathematical model (function).
The structure of an artificial neuron
is shown in Figure 4.
According to Oztemel, (2003), "the ANN is a computer based structure, designed to automate (i.e., deprived of the attainment of any assistance) the process of creating, assembling and formatting new evidence through learning, which is one of the characteristics of the human brain." an artificial neuron
is a computational model inspired by the complex natural neural system.
Elements of the artificial neuron
are represented by: m that indicates the number of the neuron input signals; [x.sub.j] the j-th neuron input signal; [w.sub.gl] the weight associated with the j-th neuron input signal g; b the threshold of each neuron, also called bias; [v.sub.g] a weighted combination of input signals and the g-th neuron bias and [phi](.) as an activation function of the g-th neuron (HAYKIN, 2001).
(b) Architecture of an artificial neuron
. (c) Diagram of the used FFNN in MATLAB.
Digital Hardware Implementation of Artificial Neuron
Model Using FPGA.
The scientists and researchers have successfully completed the development of first artificial neuron
that is amazingly capable of imitating the working of neuron cell with potential to interpret the chemical signals into electrical signals and report to other cells.