Fast prototyping of artificial neural network: GSN digital implementation

Author

Simões, Eduardo Do Valle ; Uebel, Luís Felipe ; Barone, Dante Augusto

Author_Institution

Univ. Federal do Rio Grande do Sul, Porto Alegre, Brazil

fYear

1994

fDate

26-28 Sep 1994

Firstpage

192

Lastpage

201

Abstract

This paper describes a framework for a GSN (Goal Seeking Neuron) Boolean neural network fast prototyping into an user-programmable gate array. This system provides a VHDL language description of the trained network, allowing the direct implementation of the circuit on an academic FPGA (Field-Programmable Gate Array). A GSN software tool was designed to train and simulate a user-defined network, with diverse dimensions and applications. The implemented network presents 60 neurons in four pyramids with four layers. The short propagation time (30 ns) of the network output provides the requirements to deal with real time neural applications

Keywords

Boolean functions; digital integrated circuits; field programmable gate arrays; hardware description languages; integrated circuit design; logic CAD; neural chips; real-time systems; FPGA; GSN Boolean neural network; GSN digital implementation; GSN software tool; VHDL language description; artificial neural network; fast ANN prototyping; field-programmable gate array; goal seeking neuron; real time neural applications; trained network; user-programmable gate array; Artificial neural networks; Circuit simulation; Field programmable gate arrays; Logic circuits; Neural networks; Neurons; Programmable logic arrays; Programmable logic devices; Prototypes; Topology;

fLanguage

English

Publisher

ieee

Conference_Titel

Microelectronics for Neural Networks and Fuzzy Systems, 1994., Proceedings of the Fourth International Conference on

Conference_Location

Turin

Print_ISBN

0-8186-6710-9

Type

conf

DOI

10.1109/ICMNN.1994.593265

Filename

593265