A power-efficient architecture for silicon photonic reservoir computing
Loading...
Date
2009
Journal Title
Journal ISSN
Volume Title
Publisher
EU project PHRESCO
Abstract
Reservoir 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.
Description
Keywords
Power-efficient architecture, Silicon photonic reservoir computing
Citation
Sackesyn, S., Ma, C., Katumba, A., Denis-le Coarer, F., Dambre, J., & Bienstman, P. A power-efficient architecture for silicon photonic reservoir computing.