Applying non-ideal mixed analog-digital multipliers in electronic processing circuits based on neural networks

Applying non-ideal mixed analog-digital multipliers in electronic processing circuits based on neural networks

This paper analyses effects of component mismatching and non-linearities in mixed analog-digital multipliers used in analog implementation of artificial neural networks. Function estimation and classification problems using a multilayer perceptron are studied, analyzing their results, accuracy requi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lajusticia, C., Medrano, N., Zatorre, G., Martin, B.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Analog-digital conversion
Artificial neural networks
Circuits
Energy consumption
Intelligent networks
Intelligent sensors
Multilayer perceptrons
Neural networks
Neurons
Resistors
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper analyses effects of component mismatching and non-linearities in mixed analog-digital multipliers used in analog implementation of artificial neural networks. Function estimation and classification problems using a multilayer perceptron are studied, analyzing their results, accuracy requirements and network modifications required.
DOI:10.1109/ETFA.2003.1248722