SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.11148 · 2020

Efficient On-Chip Learning for Optical Neural Networks Through Power-Aware Sparse Zeroth-Order Optimization

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Optical neural networks (ONNs) have demonstrated record-breaking potential in high-performance neuromorphic computing due to their ultra-high execution speed and low energy consumption. However, current learning protocols fail to provide scalable and efficient solutions to photonic circuit optimization in practical applications. In this work, we propose a novel on-chip learning framework to release the full potential of ONNs for power-efficient in situ training. Instead of deploying implementation-costly back-propagation, we directly optimize the device configurations with computation budgets and power constraints. We are the first to model the ONN on-chip learning as a resource-constrained stochastic noisy zeroth-order optimization problem, and propose a novel mixed-training strategy with two-level sparsity and power-aware dynamic pruning to offer a scalable on-chip training solution in practical ONN deployment. Compared with previous methods, we are the first to optimize over 2,500 optical components on chip. We can achieve much better optimization stability, 3.7x-7.6x higher efficiency, and save >90% power under practical device variations and thermal crosstalk.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2012.11148")
get_code_for_paper("2012.11148")
have("2012.11148")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2012.11148.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2012.11148.svg)](https://syntology.ai/paper/2012.11148)

Connect an agent — have() is free.