Of course, visionary dreams of bioelectronic neurocomputers
and microelectronic neuroprosetheses are unavoidable and exciting, but they should not obscure the numerous practical problems.
The prototype chip is also a step toward neurocomputers.
It will take 10 to 20 years before the method can be used to make neurocomputers in the lab.
The two main categories consist of neurocomputers
based on standard integrated circuits and ASIC.
Robert Hecht-Nielsen, inventor of one of the earliest neurocomputers
, defines a neural network as a computing system made up of a number of simple, highly interconnected processing elements which process information by their dynamic state responses to external inputs (Caudill |8~).
This situation, however, might change in the near future with the advent of neural networks (also called neurocomputers or neural systems).
Concern is sure to be voiced sooner or later by fundamentalist philosophers, but just as tools are extensions and force multipliers of the human arm and hand, neurocomputers are bound eventually to become extensions of the human mind.
Neurocomputers excel at pattern-recognition tasks when input data are fuzzy or the vision algorithm is not optimal and is difficult to ascertain.
One of the newest neurocomputers comes from Japan's NEC.
Such hybrid machines are indeed beginning to appear under the label of neurocomputers
Neurocomputers are a breed of rapidly developing hardware on which artificial neural networks are trained to solve problems.
A "controller" built into the neurocomputer then determined whether there was significant agreement between the three layers and, if agreement was reached, rendered a response.