Efficient stochastic parallel gradient descent training for on-chip optical processor

doi:10.29026/oea.2024.230182

Efficient stochastic parallel gradient descent training for on-chip optical processor

2024-01-01

1

OA

AI

DOI：10.29026/oea.2024.230182

Original

Original request for help

Save

Abstract

En 中文

In recent years, space -division multiplexing (SDM) technology, which involves transmitting data information on multiple parallel channels for efficient capacity scaling, has been widely used in fiber and free -space optical communication tems. To enable flexible data management and cope with the mixing between different channels, the integrated reconfigurable optical processor is used for optical switching and mitigating the channel crosstalk. However, efficient online training becomes intricate and challenging, particularly when dealing with a significant number of channels. Here we use stochastic parallel gradient descent (SPGD) algorithm to configure the integrated optical processor, which has less computation than the traditional gradient descent (GD) algorithm. We design and fabricate a 6x6 on -chip optical processor silicon platform to implement optical switching and descrambling assisted by the online training with the SPDG algorithm. Moreover, we apply the on -chip processor configured by the SPGD algorithm to optical communications for optical switching and efficiently mitigating the channel crosstalk in SDM systems. In comparison with the traditional GD gorithm, it is found that the SPGD algorithm features better performance especially when the scale of matrix is large, which means it has the potential to optimize large-scale optical matrix computation acceleration chips.

Keywords:

optical communications

optical signal processing

channel descrambling

optical neural network chip

silicon photonics

Efficient stochastic parallel gradient descent training for on-chip optical processor

Abstract

Journal

Organization