Biomedical Engineering Reference
In-Depth Information
Chapter 2
Classical Neural Networks
During the last few decades, neural networks have moved from theory to offering
solutions for industrial and commercial problems. Many people are interested in
neural networks from many different perspectives. Engineers use them to build
practical systems to solve industrial problems. For example, neural networks can be
used for the control of industrial processes.
There are many publications that relate to the neural network theme. Every year,
tens or even hundreds of international conferences, symposiums, congresses, and
seminars take place in the world. As an introduction to this theme we can recommend
the topics of Robert Hecht-Nielsen [
1
], Teuvo Kohonen [
2
], and Philip Wasserman
[
3
], and a more advanced topic that is oriented on the applications of neural networks
andiseditedbyA.Browne[
4
]. In this topic it is assumed that the reader has some
previous knowledge of neural networks and an understanding of their basic mechan-
isms. In this section we want to present a very short introduction to neural networks
and to highlight the most important moments in neural network development.
2.1 Neural Network History
Attempts to model the human brain appeared with the creation of the first computer.
Neural network paradigms were used for sensor processing, pattern recognition,
data analysis, control, etc. We analyze, in short, different approaches for neural
network development.
2.2 McCulloch and Pitts Neural Networks
The paper of McCulloch and Pitts [
5
] was the first attempt to understand the
functions of the nervous system. For explanation, they used very simple types of
neural networks, and they formulated the following five assumptions according to
the neuron operation:
