ABSTRACT
Neural networks are highly sophisticated pattern recognition systems that are capable of learning relationships in patterns of information. They mathematically mimic the biological human learning process and are capable of learning the hidden relationships between system inputs and responses. Neural networks mimic the learning processes of the human brain and are capable of learning relationships between patterns. Neural networks can be used in a stand-alone mode to predict biological responses, or they may be integrated as subcomponents of larger biological models. The mathematics of neural networks are derived from understanding how biological neural networks in the human brain memorize patterns and learn information. The basic computational element of a biological neural network is the neuron, which consists of synapses, dendrites, soma, and axons. An artificial neuron that mimics a biological neuron is the basic computational element in an artificial neural network. Development of a neural network requires extensive patterns or pairs of inputs and outputs.
