neural networks

A type of AI (artificial intelligence) that attempts to imitate the way the human brain works. Rather than using a digital model (in which all computations manipulate zeros and ones), a neural network creates connections between processing elements (the computer equivalent of neurons). The organization and weights of the connections determine the output, so neural networks are particularly effective for predicting events when networks have a large database of prior examples to draw on.

Neural networks are typically implemented on non-digital computers, but they can be simulated on digital computers. The field of neural networks was pioneered in the 1950's by Bernard Widrow of Stanford University.

To date, there are very few commercial applications of neural networks, but the approach is beginning to prove useful in certain areas, such as voice recognition, that involve recognizing complex patterns. For example, AOL has used a neural network filtering system to power its parental control options.