Parallel Extreme Learning Machines Based on Frequency Multiplexing

Abstract

In a recent work, we reported on an Extreme Learning Machine (ELM) implemented in a photonic system based on frequency multiplexing, where each wavelength of the light encodes a different neuron state. In the present work, we experimentally demonstrate the parallelization potentialities of this approach. We show that multiple frequency combs centered on different frequencies can copropagate in the same system, resulting in either multiple independent ELMs executed in parallel on the same substrate or a single ELM with an increased number of neurons. We experimentally tested the performances of both these operation modes on several classification tasks, employing up to three different light sources, each of which generates an independent frequency comb. We also numerically evaluated the performances of the system in configurations containing up to 15 different light sources.

Large-scale photonic natural language processing

“…To perform the classification, the output matrix H, which contains the measured optical signals, is linearly combined with a set of M trainable readout weights β (see Appendix A). In all previous PELM realizations [25,34,35,39,41], the intensities stored in H only contain information on the optical field at a single spatial or temporal plane. Here, to scale up the optical network, we exploit the entire three-dimensional optical field.…”

“…Other light-based computing architectures leverage reservoir computing (RC) [18] and extreme learning machine (ELM) [19] computational paradigms, where the input data is mapped into a feature space through a fixed set of random weights and training is performed only on the linear readout layer. Optical reservoir computers [20][21][22][23][24][25][26][27][28][29][30][31][32][33] and photonic extreme learning machines (PELMs) [34][35][36][37] apply successfully to various learning tasks, ranging from time series prediction [38,39] to image classification [40,41]. Despite the remarkable performances achieved by these architectures, their impact on large-scale problems is limited, mainly due to size constraints.…”

Integrated optical output layer for a reservoir computer based on frequency multiplexing

“…These two schemes have been demonstrated in fiber-based experimental setups. [7][8][9] The natural next step of our work is the integration of the computational substrate on photonic chips, which would improve stability and power-efficiency and reduce the system footprint, thus demonstrating the possibility of employment in real-world applications. Here we present two complementary integrated designs for the manipulation of information encoded in frequency comb lines.…”

“…Both the RC and ELM schemes potentially allow for the parallelization of different tasks, executing multiple calculations, each one based on a different frequency comb. 8 In Sec. 2 we summarize the working principle of our frequency multiplexing RC platform and we describe the fiber-based demonstration; in Sec.…”