Similar to the brain, a neural network is composed of artificial neurons (or units) and interconnections. When we view such a network as a graph, neurons can be represented as nodes (or vertices), and interconnections as edges.
Although the term "neural networks" (NNs) is most commonly used, other names include artificial neural networks (ANNs) to distinguish from the natural brain neural networks-neural nets, PDP(Parallel Distributed Processing) models (since computations can typically be performed in both parallel and distributed processing), connectionist models, and adaptive systems.
A Neuron
The basic element of the brain is a natural neuron; similarly, the basic element of every neural network is an artificial neuron, or simply neuron. That is, a neuron is the basic building block for all types of neural networks.Description of a neuron
A neuron is an abstract model of a natural neuron, as illustrated in Figure nn.01. As we can see in these figures, we have inputs x1, x2, ..., xm coming into the neuron. These inputs are the stimulation levels of a natural neuron. Each input xi is multiplied by its corresponding weight wi then the product xiwi is fed into the body of the neuron.
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjeQkRP9CzqmXPHptt-74Wz_sBnQA6TTamsBhxtgw6q001gpj7sZZ2Z1VaxiyjxwqjkRtzNkFEf7FDFcB4qgI09k6RJ9Xbwm5-Py0YVnB2kHDRPRXEWUU3YbY_wYuk0BwdDF0PRKVh0lAMy/w575-h171-no/NN01.png)
Figure nn.01
(a) A neuron model that retains the image of a natural neuron.
(b) A further abstraction of Fig. (a)
The weights represent the biological synaptic strengths in a natural neuron. The neuron adds up all the products for i = 1, m. The weighted sum of the products is usually denoted as net in the neural network literature, so we will use this notation. That is, the neuron evaluates net = x1w1 + x2w2 + ... + xmwm.
In mathematical terms, given two vectors x = (x1,x2, ...,xm) and w = (w1, w2, ..., wm), net is the dot (or scalar) product of the two vectors, x.w = x1w1 + x2w2 + ... +xmwm.
Finally, the neuron computes its output y as a certain function of net, i.e., y = ƒ(net). This function is called the activation (or sometimes transfer) function. We can think of a neuron as a sort of black box, receiving input vector x then producing a scalar output y. The same output value y can be sent out through multiple edges emerging from the neuron.
Related Posts :
Neural Network Structures
Neural Networks Single Layer
Neural Networks Multi Layer
Data Classification
Neural Network Structures
Neural Networks Single Layer
Neural Networks Multi Layer
Data Classification