Large-scale spatiotemporal photonic reservoir computer for image classification

04/06/2020
by   Piotr Antonik, et al.
0

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 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.

READ FULL TEXT

page 1

page 6

page 12

research
04/11/2016

Reservoir computing for spatiotemporal signal classification without trained output weights

Reservoir computing is a recently introduced machine learning paradigm t...
research
11/17/2017

Bidirectional deep-reservoir echo state networks

We propose a deep architecture for the classification of multivariate ti...
research
06/04/2020

Neural Network for Low-Memory IoT Devices and MNIST Image Recognition Using Kernels Based on Logistic Map

The study presents a neural network, which uses filters based on logisti...
research
11/17/2017

Bidirectional deep-readout echo state networks

We propose a deep architecture for the classification of multivariate ti...
research
11/17/2017

Bidirectional deep echo state networks

In this work we propose a deep architecture for the classification of mu...
research
09/18/2017

Combinational neural network using Gabor filters for the classification of handwritten digits

A classification algorithm that combines the components of k-nearest nei...

Please sign up or login with your details

Forgot password? Click here to reset