Silicon Photonic Filter-based Dot Product Engine for Convolutional Neural Networks
Lorenzo De Marinis, Marc Sorel, Charalambos Klitis, G. Contestabile, Nicola Andriolli · OSA Advanced Photonics Congress 2021 · 2021
We present a silicon photonic filter-based analog engine for 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.