High-Speed Photonic Reservoir Computing Using a Time-Delay-Based Architecture: Million Words per Second Classification
By Laurent Larger, A. Baylón-Fuentes, R. Martinenghi, V. Udaltsov, Yanne K. Chembo, Maxime Jacquot. 2017
448 citations recorded by the source corpus.
A brain-inspired computer made with optoelectronic parts runs faster thanks to a hardware redesign, recognizing simple speech at the rate of 1 million words per second
Subfields: Artificial Intelligence, Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/5b9ff454a6fbccbc6ff81792accb6f8f43d4cc70
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Petros Koumoutsakos
- Themistoklis P. Sapsis
- Pantelis R. Vlachas
- Michelle Girvan
- Jaideep Pathak
- Edward Ott
- Brian R. Hunt
- Seiji Takeda
In Electrical and Electronic Engineering
- Edward Ott
- Seiji Takeda
- Petros Koumoutsakos
- Brian R. Hunt
- Gouhei Tanaka
- Naoki Kanazawa
- Daiju Nakano
- Toshiyuki Yamane
Citations in the corpus
- Emerging opportunities and challenges for the future of reservoir computing (2024, unknown): “…in experimental settings and an active line of researchistoexplorenewtypesofnonlineardynamicssuchaselectro-optic phase-delay dynamics 28 – 30 , optical scattering 31,32 , dynamic memristors 33 – 36 , enlarged memory capacity in chaotic dynamics 37 , solitons 38 and quantum states 39,40 .”
- Backpropagation algorithms and Reservoir Computing in Recurrent Neural Networks for the forecasting of complex spatiotemporal dynamics (2019, methodology): “Inthis work, we consider reservoir computers with f given by the functional form where and Larger et al. (2017, 2012) Following Jaeger and Haas (2004), where ω is a hyperparameter.”
- Recent Advances in Physical Reservoir Computing: A Review (2018, background): “For instance, in speech recognition tasks, the number of words processed per second under a very low word error rate condition is a measure for processing speed (Larger et al., 2017).”