A CAD approach to the design of a neural network simulator

Author

Giacinti, M. ; Latini, G. ; Campolucci, P. ; Piazza, F.

Author_Institution

Dipt. di Elettronica e Autom., Ancona Univ., Italy

Volume

4

fYear

1999

fDate

6/21/1905 12:00:00 AM

Firstpage

2398

Abstract

This paper shortly describes a preliminary version of a new discrete-time network software simulator implemented using the signal-flow-graph (SFG) approach. The software is able to do a very user-friendly schematic entry of the network and the cost function, and can implement any discrete-time network composed by delays, linear and nonlinear fired or adaptable components (also user-defined). Structures such as usual linear filters (FIR, IIR) and static multilayer, time delay or recurrent neural networks of arbitrary topologies can be easily adapted with respect to any user-selected parameters, minimizing any objective function that can be described by a SFG (online, batch, windowed MSE, etc.) using the BC method

Keywords

computer aided software engineering; delays; digital simulation; filtering theory; graphical user interfaces; minimisation; neural nets; signal flow graphs; virtual machines; CAD; FIR filters; IIR filters; SFG approach; adaptable components; cost function; delays; discrete-time network; discrete-time network software simulator; fired components; linear components; linear filters; minimization; neural network simulator design; nonlinear components; objective function; recurrent neural networks; signal-flow-graph approach; static multilayer neural networks; time delay neural networks; user-friendly schematic entry; user-selected parameters; Cost function; Delay effects; Delay lines; Design automation; Finite impulse response filter; IIR filters; Multi-layer neural network; Neural networks; Nonlinear filters; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1999. IJCNN '99. International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-5529-6

Type

conf

DOI

10.1109/IJCNN.1999.833443

Filename

833443