Reservoir computing with nonlinear optical media

• Type: Article in International Conference Proceedings Book
• Date: 2022

Authors

Ferreira, TD (Author) Other; Silva, NA (Author) Other; Silva, D (Author) Other; Rosa, CC (Author) FCUP; Guerreiro, A (Author) FCUP

Conference proceedings International

Title: Journal of Physics: Conference Series

5th International Conference on Applications of Optics and Photonics, AOP 2022

17 July 2022 through 22 July 2022

Indexing

Scopus

Other information

Authenticus ID: P-00X-Q82

DOI: 10.1088/1742-6596/2407/1/012019

Abstract (EN): Reservoir computing is a versatile approach for implementing physically Recurrent Neural networks which take advantage of a reservoir, consisting of a set of interconnected neurons with temporal dynamics, whose weights and biases are fixed and do not need to be optimized. Instead, the training takes place only at the output layer towards a specific task. One important requirement for these systems to work is nonlinearity, which in optical setups is usually obtained via the saturation of the detection device. In this work, we explore a distinct approach using a photorefractive crystal as the source of the nonlinearity in the reservoir. Furthermore, by leveraging on the time response of the photorefractive media, one can also have the temporal interaction required for such architecture. If we space out in time the propagation of different states, the temporal interaction is lost, and the system can work as an extreme learning machine. This corresponds to a physical implementation of a Feed-Forward Neural Network with a single hidden layer and fixed random weights and biases. Some preliminary results are presented and discussed. © Published under licence by IOP Publishing Ltd.

Language: English

Type (Professor's evaluation): Scientific