Scalable mean rate signal encoding analog neural network

Scalable mean rate signal encoding analog neural network

A micropower feedforward neural network implementation in standard CMOS using pulse frequency modulated signal representation is presented in this paper. The implementation includes a modified backpropagation algorithm using analog UV-programmable floating gate memories for weight storage. Measureme...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Berg, Y., Ruth, J.-E., Lande, T.S.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Biological neural networks
Circuits
Encoding
Feedforward neural networks
Feedforward systems
Neural networks
Neurons
Pulse measurements
Stochastic processes
Stochastic resonance
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A micropower feedforward neural network implementation in standard CMOS using pulse frequency modulated signal representation is presented in this paper. The implementation includes a modified backpropagation algorithm using analog UV-programmable floating gate memories for weight storage. Measurements of a 3-6-2 layered feedforward neural network implementation solving the 3-parity problem are shown.
DOI:10.1109/ISCAS.1995.523731