English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Photonic technologies have shown a promising way to build high-speed andhigh-energy-efficiency neural network accelerators. In previously presentedphotonic neural networks, architectures are mainly designed for fully-connectedlayers. When convolutional layers are executed in such neural networks, thelarge-scale electrooptic modulation array heavily increases the energydissipation on chip. To increase the energy efficiency, here we show anintegrated photonic architecture specifically for convolutional layercalculations. Optical delay lines replace electronics to execute datamanipulations on optical chip, reducing the scale of electro-optic modulationarray. Consequently, the energy dissipation of these parts is mitigated.Powered by wavelength division multiplexing, the footprint of delay lines issignificantly reduced compared with previous art, thus being practical tofabricate. We evaluate the potential performance of the proposed architecturewith respect to component flaws in practical fabrications. According to theresults, with well-controlled system insertion loss, energy efficiency of theproposed architecture would surpass previously presented works and thestate-of-art electronic processors. We anticipate the proposed architecture isbeneficial for future fast and energy-efficient convolutional neural networkaccelerators.

Performance evaluation of an integrated photonic convolutional neural network based on delay buffering and wavelength division multiplexing