artificial neural network

(redirected from Artificial neural networks)
Also found in: Medical, Wikipedia.

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 ?
Having emerged in the late 2000s, Deep Learning is a revolutionary artificial intelligence technology that allows the training of artificial neural networks on large volumes of data.
We have recently demonstrated how it is possible to implement large-scale artificial neural networks and real-time sensory motor systems in VLSI technology, exploiting the physics of silicon to reproduce the biophysics of neural systems.
Deep learning is basically researchers making use of training systems knowns as artificial neural networks on information that had been derived from inputs such as audio and images.
These techniques called artificial neural networks are, in effect, simplified models of the central nervous system and they transfer the laws beyond the data to the network structure by processing the experimental data in the same manner as done by the brain.
Among the topics are how to construct personalized cognitive structures, illumination-invariant face recognition with a whitening filter and local binary patterns, an intelligence gathering system for business based on cloud computing, a new camera calibration based on a neural network with runable activation function in intelligent space, forecasting monthly maximum five-day precipitation using artificial neural networks with initial lags, the design of an elderly tumble detection system based on a fuzzy algorithm, temperature compensation in full optical fiber current transformer using signal processing, and concessionaire selection based on an improved lowest tariff decision model.
The application of artificial neural networks (namely time-lagged feed-forward neural networks) for prediction of passenger traffic flows was described by T.
On the other hand, because of their multidisciplinary nature, artificial neural networks are commonly applied by the majority of researchers working in different branches of science (Goh et al.
Summary: I did spend more than 10 years doing research on designing microchips - called artificial neural networks (ANN) - which mimic how the human brain processes information.
In this context, the use of Artificial Neural Networks (ANN) can be considered an alternative approach for predicting soil penetration resistance from soil bulk density and water content.
According to many previous works, Artificial Neural Networks Datta et al(1997), Kalogirou (2006), and Salem (2011) have proved its ability to model and predict the energy consumption in different types of buildings.
Artificial neural networks have been shown to yield superior predictive capability compared with the multiple linear regression model.
Self Organizing Feature Maps [1] are special class of artificial neural networks based on competitive learning.

Full browser ?