A power-efficient architecture for silicon photonic reservoir computing

Simple item page
dc.contributor.authorSackesyn, Stijn
dc.contributor.authorMa, Chonghuai
dc.contributor.authorKatumba, Andrew
dc.contributor.authorDenis-le Coarer, Florian
dc.contributor.authorDambre, Joni
dc.contributor.authorBienstman, Peter
dc.date.accessioned2022-11-27T17:00:59Z
dc.date.available2022-11-27T17:00:59Z
dc.date.issued2009
dc.description.abstractReservoir computing is a machine learning technique in which a nonlinear dynamical system which is also called the reservoir is used for computation. While it was originally implemented as an efficient way to train a neural network [1], it has now grown to a method which is commonly used for classification and regression tasks. Unlike other techniques which optimize the recurrent neural network (RNN) itself to solve a task, the RNN is not modified during training in reservoir computing. Instead, a linear combination is used to train an optimal classifier in the high dynamical state space to which the signal is projected by propagation through the reservoir. By keeping the recurrent network unchanged and train only on the level of the linear output layer makes reservoir computing a computationally cheap method.en_US
dc.identifier.citationSackesyn, S., Ma, C., Katumba, A., Denis-le Coarer, F., Dambre, J., & Bienstman, P. A power-efficient architecture for silicon photonic reservoir computing.en_US
dc.identifier.urihttps://photonics.intec.ugent.be/download/pub_4488.pdf
dc.identifier.urihttps://nru.uncst.go.ug/handle/123456789/5484
dc.language.isoenen_US
dc.publisherEU project PHRESCOen_US
dc.subjectPower-efficient architectureen_US
dc.subjectSilicon photonic reservoir computingen_US
dc.titleA power-efficient architecture for silicon photonic reservoir computingen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A power-efficient architecture for silicon photonic.pdf
Size:
196.52 KB
Format:
Adobe Portable Document Format
Description:
Article
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Engineering and Technology