Photonic delay systems as machine learning implementations

MaRDI QIDQ5744834zbMATH OpenFDO

Authors Michiel Hermans, Miguel Soriano, Joni Dambre, Peter Bienstman, Ingo Fischer

Publication date 19 February 2016

Full work available at URL https://arxiv.org/abs/1501.02592, http://jmlr.csail.mit.edu/papers/v16/hermans15a.html

zbMATH Keywords

machine learning modelsoptical computingrecurrent neural networks

Mathematics Subject Classification ID

Mathematical problems of computer architecture (68M07) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• An introduction to delay-coupled reservoir computing
• Complicated Dynamics of a Delayed Photonic Reservoir Computing System
• Computing by means of physics-based optical neural networks
• Reservoir Computing
• Deep time-delay reservoir computing: dynamics and memory capacity

Cited in

(4)

• A novel fractional gradient-based learning algorithm for recurrent neural networks
• Stability analysis of reservoir computers dynamics via Lyapunov functions
• Complicated Dynamics of a Delayed Photonic Reservoir Computing System
• Reservoir computing with random and optimized time-shifts

This page was built for publication: Photonic delay systems as machine learning implementations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5744834)