A description is given of the development and use of a modular system for neural network simulation, called NNET. The aim was to provide tools that are both flexible in use and efficient in execution. Things to be simulated are collections of many simple processing elements, the neurons, connected to each other, potentially running in parallel, and communicating through the connections between them. The implementation of this computational structure through its simulation on traditional computers requires efficient hardware to reproduce parallel processing and good software to permit easy definition and testing of the (often complex) structure of a net of connected neurons. NNET is based on a neural network simulating nucleus, with a library of efficient C functions describing some current model, a compiled low-level language for the description of nets, a text-video interface to assist the user during the simulations, and an interpreted structured language to control the operations on all of the simulating environment. Some possible further developments of NNET are discussed.
Ferretti, C., Mauri, G. (1990). NNET: some tools for Neural NETworks simulation. In Proc. 9th IEEE Annual Int. Phoenix Conf. on Computers and Communications (pp.38-43). New York : IEEE Computer Society [10.1109/PCCC.1990.101598].
NNET: some tools for Neural NETworks simulation
FERRETTI, CLAUDIO;MAURI, GIANCARLO
1990
Abstract
A description is given of the development and use of a modular system for neural network simulation, called NNET. The aim was to provide tools that are both flexible in use and efficient in execution. Things to be simulated are collections of many simple processing elements, the neurons, connected to each other, potentially running in parallel, and communicating through the connections between them. The implementation of this computational structure through its simulation on traditional computers requires efficient hardware to reproduce parallel processing and good software to permit easy definition and testing of the (often complex) structure of a net of connected neurons. NNET is based on a neural network simulating nucleus, with a library of efficient C functions describing some current model, a compiled low-level language for the description of nets, a text-video interface to assist the user during the simulations, and an interpreted structured language to control the operations on all of the simulating environment. Some possible further developments of NNET are discussed.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
