artificial neural network

(redirected from Neural computing)
Also found in: Dictionary, Medical.

artificial neural network

(artificial intelligence)
(ANN, commonly just "neural network" or "neural net") A network of many very simple processors ("units" or "neurons"), each possibly having a (small amount of) local memory. The units are connected by unidirectional communication channels ("connections"), which carry numeric (as opposed to symbolic) data. The units operate only on their local data and on the inputs they receive via the connections.

A neural network is a processing device, either an algorithm, or actual hardware, whose design was inspired by the design and functioning of animal brains and components thereof.

Most neural networks have some sort of "training" rule whereby the weights of connections are adjusted on the basis of presented patterns. In other words, neural networks "learn" from examples, just like children learn to recognise dogs from examples of dogs, and exhibit some structural capability for generalisation.

Neurons are often elementary non-linear signal processors (in the limit they are simple threshold discriminators). Another feature of NNs which distinguishes them from other computing devices is a high degree of interconnection which allows a high degree of parallelism. Further, there is no idle memory containing data and programs, but rather each neuron is pre-programmed and continuously active.

The term "neural net" should logically, but in common usage never does, also include biological neural networks, whose elementary structures are far more complicated than the mathematical models used for ANNs.

See Aspirin, Hopfield network, McCulloch-Pitts neuron.

Usenet newsgroup:
References in periodicals archive ?
For this reason, many of the underlying research questions around neural computing center around what aspects of biological neural computing should be emulated, as how to build neural architectures is increasingly well understood.
Vitela, J, Achar, E, "Modeling, Prediction and Analysis of Alkyd Enamel Coating Properties via Neural Computing.
The power of neural computing comes from the threshold concept.
The final chapter considers the process of modeling and memorizing physical events as stochastic processes, and approaches the problem of neural computing from a different angle than digital computers.
Yet Robert, who has worked with the Neural Computing Research Group at Birmingham since 1993, is not one to worry about such criticism.
Neural Computing Systems (Irvine, CA) will develop a scattering-based computer-aided tomography approach to target modeling and discrimination using high-range resolution and synthetic-aperture-radar data.
Neural computing should not be viewed as a competitor to conventional computing, but rather as a complementary technique.
It also seems appropriate to use the advanced pattern recognition techniques available in neural computing methods.
Nima Nattagh, an analyst at Financial Neural Computing Inc.
The concept of neural analysis is not new, but it is only recently that technology has advanced sufficiently to allow the development and application of neural computing systems.
Interesting technology such as neural computing will give us higher levels of assurance.
In addition to these more standard models, we are experimenting with neural computing for some of our more difficult revenue streams.