Computational Intelligence Techniques - Computational Intelligence in Biomedical Engineering - page 77

3.2 Artificial Neural Networks
The ANN is an information-processing paradigm inspired by the structure of
biological nervous systems such as the human brain. The primary character-
istic of this paradigm is modelling the core information-processing system as
a neuron and building a network composed of a large number of highly inter-
connected neurons working to solve specific problems. ANNs were the earliest
attempts to mimic human intelligence with a machine and it was generally
accepted that learning in biological systems involved developing interneuron
synaptic connections. The key concepts therefore are the characteristics of
the neuron, the neuron interconnections, and the neuron activation system
consisting of several mathematical functions.
The discovery of the neuron is primarily attributed to Ramon y Cajal (Jain
et al., 1996), who postulated that the nervous system was made up of an
interconnected network of polarized neurons. This discovery led to the 1906
Nobel Prize in Physiology or Medicine, which he shared with his contempo-
rary Camillo Golgi who had shown that a silver chromate solution could be
used to stain brain tissue and reveal the interconnected network of neurons.
The major parts of a biological neuron (see Figure 3.2) are the cell body,
which contains the nucleus and a branching dendritic tree that collects sig-
nals from neighboring neurons. The neuron's output is transmitted via the
axon, which forms a connection or synapse with the dendrites of neighboring
neurons (see Figure 3.3). The nucleus is the processing center, which inte-
grates the input signals and generates a response that is a nonlinear function
of the inputs and the internal state. The neuron alone does not possess consid-
erable information-processing capabilities, but a large network formed from
these single neurons gives rise to special processing abilities. We will see later
Cell body
Nucleus
Axon
Dendrites
FIGURE 3.2
A neuron collects input signals from nearby neurons through the dendrites,
integrates the signals, and produces an output response to other neurons via
the axon.