A neural network is an AI system that is capable of finding and differentiating patterns. It is most useful for identification, classification, and prediction when a vast amount of information is available. By examining hundreds, or even thousands of examples, a neural network detects important relationships and patterns in the information. Neural Networks attempt to mimic the structure and functioning of the human brain.
Types of Neural Networks
Self-Organizing Neural Network:finds patterns and relationships in vast amounts of data by itself.
Back-propagation neural network: A neural network trained by someone else. You teach the network the same way you would a child
Comparing artificial neural network (ANN) to the home computer
Let us start with the home computer and the way it processes information. The CPU knows of specific locations where it can access its instructions and data. Furthermore, the CPU by accessing the instructions and the data, and running them through the CPU, then takes the results and retains them in a designated section of memory. This process is consistent and rigid with no deviation.
On the other hand, the artificial neural network (ANN) is neither consistent nor rigid with much deviation in its process that does not rely on predefined instructions or the actual storage of data in a designated section of memory. Instead of a Central Processor handling all of the processing, multiple less complex processors take the subjected data from the other processors within the neural network. This produces the results of what the ANN had learned. http://pages.cs.wisc.edu/~bolo/shipyard/neural/local.html