Artificial neural networks for photonic applications—from algorithms to implementation: tutorial

Abstract

This tutorial–review on applications of artificial neural networks in photonics targets a broad audience, ranging from optical research and engineering communities to computer science and applied mathematics. We focus here on the research areas at the interface between these disciplines, attempting to find the right balance between technical details specific to each domain and overall clarity. First, we briefly recall key properties and peculiarities of some core neural network types, which we believe are the most relevant to photonics, also linking the layer’s theoretical design to some photonics hardware realizations. After that, we elucidate the question of how to fine-tune the selected model’s design to perform the required task with optimized accuracy. Then, in the review part, we discuss recent developments and progress for several selected applications of neural networks in photonics, including multiple aspects relevant to optical communications, imaging, sensing, and the design of new materials and lasers. In the following section, we put a special emphasis on how to accurately evaluate the complexity of neural networks in the context of the transition from algorithms to hardware implementation. The introduced complexity characteristics are used to analyze the applications of neural networks in optical communications, as a specific, albeit highly important example, comparing those with some benchmark signal-processing methods. We combine the description of the well-known model compression strategies used in machine learning, with some novel techniques introduced recently in optical applications of neural networks. It is important to stress that although our focus in this tutorial–review is on photonics, we believe that the methods and techniques presented here can be handy in a much wider range of scientific and engineering applications.

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

“…A meaningful example is diffractive optical neural networks, using semitransparent mirrors or beam splitters to establish shortcut connections between neural network layers. 330 This configuration may result in more efficient information transmission and connectivity than traditional ANN, benefiting from high bandwidth, parallel processing, and low latency. 331 Biomimetic sensors also benefit from DNN, with synesthesia models 332 outperforming human perception of chemical mixtures.…”

“…In this subsection, the integration of sensors with DNN was showcased, demonstrating a symbiotic relationship through signal processing theory. A meaningful example is diffractive optical neural networks, using semitransparent mirrors or beam splitters to establish shortcut connections between neural network layers . This configuration may result in more efficient information transmission and connectivity than traditional ANN, benefiting from high bandwidth, parallel processing, and low latency .…”

Multimode diffractive optical neural network

“…1 These challenges promote the research enthusiasm of optical neural networks (ONNs). 2,3 This is attributed to the high bandwidth and high parallelism characteristics of light, which are manifested in the ONNs composed of Mach-Zehnder interferometers (MZIs), [4][5][6] micro-rings resonators (MRRs), [7][8][9] scattering 10 and diffraction [11][12][13][14][15] structures. It is worth noting that on-chip ONN is more competitive on portability and footprint, and even some commercial companies have been established.…”

“…Current electronic computing devices are faced with the challenges of limited bandwidth, high power consumption, and high cost 1 . These challenges promote the research enthusiasm of optical neural networks (ONNs) 2 , 3 . This is attributed to the high bandwidth and high parallelism characteristics of light, which are manifested in the ONNs composed of Mach–Zehnder interferometers (MZIs), 4 – 6 micro-rings resonators (MRRs), 7 – 9 scattering 10 and diffraction 11 – 15 structures.…”

Conditional Recurrent Neural Networks for broad applications in nonlinear optics

“…It has been extensively applied in image recognition and classification [3,4], natural language processing [5], time-series prediction [6], cybersecurity [7], healthcare [8], autonomous vehicle control [9] and neuroscience research [10]. In the recent years, machine learning techniques have also been developed for different applications in optics [11][12][13], such as inverse design of photonic structures [14], and optical microscopy [15].…”