Neural network or Artificial Neural Network (ANN) is a massively parallel distributed processor made up of simple processing units, which has a natural propensity for storing experiential knowledge and making it available for use. A neural network contains a large number of simple neuron like processing elements and a large number of weighted connections encode the knowledge of a network. Though biologically inspired, many of the neural network models developed do not duplicate the operation of the human brain.
The intelligence of a neural network emerges from the collective behavior of neurons. Each neuron performs only very limited operation. Even though each individual neuron works slowly, they can still quickly find a solution by working in parallel. This fact can explain why humans can recognize a visual scene faster than a digital computer though an individual brain cell responds much more slowly than a digital cell in a VLSI circuit.
The brain-style computation points out a new direction for building an intelligent system, a direction which is fundamentally different from the symbolic approach. By now, more than a dozen well-known neural network models have been built. These include Backpropagation net, ART, Hopfield net, Bolzmann machine, etc., each has different performance features.
ANN represents a technology that is rooted in many disciplines: neuroscience, mathematics, statistics, physics, computer science and engineering. ANN find applications in such diverse fields such as modelling, time series analysis, pattern recognition, signal processing, and control by virtue of an important property: the ability to learn from input data with or without a teacher.