Large-scale spatiotemporal photonic reservoir computer for image classification

Abstract

We propose a scalable photonic architecture for implementation of feedforward and recurrent neural networks to perform the classification of handwritten digits from the MNIST database. Our experiment exploits off-the-shelf optical and electronic components to currently achieve a network size of 16,384 nodes. Both network types are designed within the the reservoir computing paradigm with randomly weighted input and hidden layers. Using various feature extraction techniques (e.g. histograms of oriented gradients, zoning, Gabor filters) and a simple training procedure consisting of linear regression and winner-takes-all decision strategy, we demonstrate numerically and experimentally that a feedforward network allows for classification error rate of 1%, which is at the state-of-the-art for experimental implementations and remains competitive with more advanced algorithmic approaches. We also investigate recurrent networks in numerical simulations by explicitly activating the temporal dynamics, and predict a performance improvement over the feedforward configuration.

12 pages, 9 figures

References in corpus (6)

• Optoelectronic Reservoir Computing
• All-optical Reservoir Computing
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• Reservoir computing with a single time-delay autonomous Boolean node
• Reservoir computing with the frequency, phase and amplitude of spin-torque nano-oscillators
• Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation

Cited by in corpus (8)

• Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
• Reservoir computing based on a silicon microring and time multiplexing for binary and analog operations
• Photonic neural networks based on integrated silicon microresonators
• An array of microresonators as a Photonic Extreme Learning Machine
• High Speed Human Action Recognition using a Photonic Reservoir Computer
• Energy-efficient neural network inference with microcavity exciton-polaritons
• Emergent self-adaptation in an integrated photonic neural network for backpropagation-free learning
• Stochastic Reservoir Computers