2280

By starting with a one-neuron model, it may be easier to understand the neural

network structure. A neuron is defined as an information-processing unit that is fun-

model to illustrate the neural network structure.

As shown in Fig. 3, there are three basic elements in an ANN:

(a) A set of *connecting links*, *w*, each of which is characterized by a *weight *of its

own. The weights on the connections from the input *X*i (*i *= 1, ..., *n*) to the neuron

(b) An *adder*, , for summing the weighted input signals; the operation constitute

a linear combiner, *v*:

w2x2

....

wnxn

w1x1

(1)

(b) An *activation function*, *f(.), *for limiting the amplitude of the output of a neuron.

The output from the neuron model can be described by

f(*v*)

(2)

There are several types of activation functions. Examples of activation functions

related to this study are given below.

i) linear function:

0

(3)

ii) sigmoid function:

1

(4)

exp( a*v*)

1

where *a *is the slope parameter

Fig. 3.

One neuron structure.