Silicon photonic filter-based dot product engine for convolutional neural networks
Contributo in Atti di convegno
Data di Pubblicazione:
2021
Abstract:
We present a silicon photonic filter-based a nalog e ngine f or computing dot products in convolutional neural networks. It shows a greater energy efficiency compared to electronic solutions with a limited bit resolution degradation of input signals.
Tipologia CRIS:
04.01 Contributo in Atti di convegno
Keywords:
analog computing; photonic neural networks; convolutional neural networks; dot product; silicon photonics
Elenco autori:
Andriolli, Nicola
Link alla scheda completa: