Embodiment of Learning in Electro-Optical Signal Processors

Abstract

Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing. In particular it has recently been demonstrated, using the artificial intelligence algorithm known as reservoir computing, that photonic implementations of such systems solve complex tasks such as speech recognition. Here we show how the backpropagation algorithm can be physically implemented on the same electro-optical delay-coupled architecture used for computation with only minor changes to the original design. We find that, compared when the backpropagation algorithm is not used, the error rate of the resulting computing device, evaluated on three benchmark tasks, decreases considerably. This demonstrates that electro-optical analog computers can embody a large part of their own training process, allowing them to be applied to new, more difficult tasks.

Main text (5 pages, 2 figures) merged with the supplementary material (8 pages, 5 figures)

References in corpus (3)

• High performance photonic reservoir computer based on a coherently driven passive cavity
• Reservoir computing with a single time-delay autonomous Boolean node
• Trainable and Dynamic Computing: Error Backpropagation through Physical Media

Cited by in corpus (7)

• Recent Advances in Physical Reservoir Computing: A Review
• Tutorial: Photonic Neural Networks in Delay Systems
• Coupled nonlinear delay systems as deep convolutional neural networks
• Neural Schrödinger Equation:Physical Law as Neural Network
• Deep Photonic Reservoir Computer for Speech Recognition
• Boolean learning under noise-perturbations in hardware neural networks
• A Unifying Framework for Information Processing in Stochastically Driven Dynamical Systems