Neuro-MMI: A Hybrid Photonic-Electronic Machine Learning Platform
Authors:
- Nicholas SouresNSNicholas Soures
- Jeffrey SteidleJSJeffrey Steidle
- Stefan PrebleSPStefan Preble
- Dhireesha KudithipudiDKDhireesha Kudithipudi
- 1 July 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 187-188
Abstract
We demonstrate a hybrid electronic-photonic feedforward neural network which exploits interference patterns in a Multimode Interference coupler (neuro-MMI). The proposed neuro-MMIs accuracy is statistically equivalent to state-of-the-art networks. Neuro-MMI serves as a blueprint for a class of high-performance neuromorphic networks that can solve cognitive tasks.Keywords
This publication has 4 references indexed in Scilit:
- Neuromorphic photonic networks using silicon photonic weight banksScientific Reports, 2017
- Deep learning with coherent nanophotonic circuitsNature Photonics, 2017
- The No-Prop algorithm: A new learning algorithm for multilayer neural networksNeural Networks, 2013
- Extreme learning machine: a new learning scheme of feedforward neural networks2005