`

Timezone: »

 
Oral
Reservoir Computing meets Recurrent Kernels and Structured Transforms
Jonathan Dong · Ruben Ohana · Mushegh Rafayelyan · Florent Krzakala

Wed Dec 09 06:15 AM -- 06:30 AM (PST) @ Orals & Spotlights: Deep Learning

Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where internal weights are fixed at random and only a linear output layer is trained. In the large size limit, such random neural networks have a deep connection with kernel methods. Our contributions are threefold: a) We rigorously establish the recurrent kernel limit of Reservoir Computing and prove its convergence. b) We test our models on chaotic time series prediction, a classic but challenging benchmark in Reservoir Computing, and show how the Recurrent Kernel is competitive and computationally efficient when the number of data points remains moderate. c) When the number of samples is too large, we leverage the success of structured Random Features for kernel approximation by introducing Structured Reservoir Computing. The two proposed methods, Recurrent Kernel and Structured Reservoir Computing, turn out to be much faster and more memory-efficient than conventional Reservoir Computing.

Author Information

Jonathan Dong (Laboratoire Kastler-Brossel)
Ruben Ohana (Ecole Normale Supérieure & LightOn)
Mushegh Rafayelyan (Kastler-Brossel Laboratory (ENS, Sorbonne U., PSL U., CNRS, Collège de France))
Florent Krzakala (ENS Paris, Sorbonnes Université & EPFL)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors