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/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Reservoir computers (RC) are randomized recurrent neural networks welladapted to process time series, performing tasks such as nonlinear distortioncompensation or prediction of chaotic dynamics. Deep reservoir computers(deep-RC), in which the output of one reservoir is used as the input foranother one, can lead to improved performance because, as in other deepartificial neural networks, the successive layers represent the data in moreand more abstract ways. We present a fiber-based photonic implementation of atwo-layer deep-RC based on frequency multiplexing. The two RC layers areencoded in two frequency combs propagating in the same experimental setup. Theconnection between the layers is fully analog and does not require any digitalprocessing. We find that the deep-RC outperforms a traditional RC by up to twoorders of magnitude on two benchmark tasks. This work paves the way towardsusing fully analog photonic neuromorphic computing for complex processing oftime series, while avoiding costly analog-to-digital and digital-to-analogconversions.

Deep Photonic Reservoir Computer Based on Frequency Multiplexing with Fully Analog Connection Between Layers