Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation

TL;DR

This tutorial-review addresses the integration of artificial neural networks with photonics, focusing on architecture choices, complexity-aware design, and hardware realizations. It surveys a spectrum of NN types—dense, CNNs, RNNs, LSTMs, GRUs, ESNs, attention- and transformer-based models, residual and RBF networks, autoencoders, and GANs—grounding their use in optical contexts and photonic hardware. It highlights practical challenges in hyperparameter optimization, model compression, and end-to-end learning for applications spanning optical communications, sensing, imaging, and materials design, with emphasis on complexity metrics and implementation strategies. The work emphasizes physics-informed and data-driven approaches (PINNs, NFT-based processing, FNOs, domain randomization) and advocates for integrated design of algorithms and photonic hardware to realize real-time, energy-efficient, scalable photonic systems. Overall, the paper argues that exploiting NN-based methods with careful complexity reduction and hardware-aware training can unlock substantial gains in speed, accuracy, and adaptability across photonics disciplines, enabling next-generation smart photonic devices and digital twins.

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.

Figures (32)

• Figure 1: Schematics of a McCulloch-Pitts Neuron.
• Figure 2: Optical implementations of vector-matrix multipliers.
• Figure 3: Schematics of 1D and 2D convolutional filters. A series of arrays of such filters constitute a convolutional neural network.
• Figure 4: Optical 2D convolution using scattering matrix in a Fourier plane of a 4-f imaging system.
• Figure 5: Schematics of a recurrent neural network. Hidden layer neurons with closed-loop connections underlie the memory effect.