In the literature a wide variety of definitions and explanations for the terms Artificial Neural Network and Neural Computing can be found. The following definitions are balanced towards computing but are nevertheless very comprehensive in my opinion and they offer a wide range of views of what an ANN is.
The definition by Igor Aleksander is including a very wide range of methods and applications in the field of neural computing:
``Neural computing is the study of networks of adaptable nodes which, through a process of learning from task examples, store experimental knowledge and make it available for use.'' [alek95, p1,].
The following description by Laurene Fausett of artificial neural networks includes only the connectionist research approach [faus94, p3,].
``An artificial neural network is an information-processing system that has certain performance characteristics in common with biological neural networks. Artificial neural networks have been developed as generalizations of mathematical models of human cognition or neural biology, based on the assumption that:
- Information processing occurs at many simple elements called neurons.
- Signals are passed between neurons over connection links.
- Each connection link has an associated weight, which, in a typical neural net, multiplies the signal transmitted.
- Each neuron applies an activation function (usually nonlinear) to its net input (sum of weighted input signals) to determine its output signal.''
Robbert L. Harvey focuses very much on the biological model. His definition excludes most parts of logical neural networks from the field of neural networks.
``A neural network is a dynamical system with one-way interconnections. It carries out processing by its response to inputs. The processing elements are nodes; the interconnects are directed links. Each processing element has a single output signal from which copies fan out.'' [harv94, p2f,]
The author of this report has the following definition which is more concerned with the fundamental ideas of neural systems and the basic properties of the brain rather than the aspect of modeling parts of the nervous system.