Design of a hybrid digital-analog neural co-processor for signal processing

Design of a hybrid digital-analog neural co-processor for signal processing

A hybrid architecture for neural coprocessing is presented. A fixed set of analog multipliers and capacitors (analog memory) emulates multilayer perceptrons through digitally-controlled multiplexing. Thus parallelism is partially preserved without direct analog implementation of the whole structure....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Romariz, A.R.S., Ferreira, P.U.A., Campelo, J.V., Graciano, M.L., da Costa, J.C.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Analog memory
Capacitors
Circuits
Control systems
Coprocessors
Digital-analog conversion
Multilayer perceptrons
Neurons
Parallel processing
Signal design
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A hybrid architecture for neural coprocessing is presented. A fixed set of analog multipliers and capacitors (analog memory) emulates multilayer perceptrons through digitally-controlled multiplexing. Thus parallelism is partially preserved without direct analog implementation of the whole structure. Details of system VLSI implementation are given, along with simulation results and performance estimation.
ISSN:1089-6503
2376-9505
DOI:10.1109/EURMIC.1996.546477