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.

We leverage the attention mechanism to investigate and comprehend the contribution of each input symbol of the input sequence and their hidden representations for predicting the received symbol in the bidirectional recurrent neural network (BRNN)-based nonlinear equalizer. In this paper, we propose an attention-aided novel design of a partial BRNN-based nonlinear equalizer, and evaluate with both LSTM and GRU units in a single-channel DP-64QAM 30Gbaud coherent optical communication systems of 20 × 50 km standard single-mode fiber (SSMF) spans. Our approach maintains the Q-factor performance of the baseline equalizer with a significant complexity reduction of ∼56.16% in the number of real multiplications required to equalize per symbol (RMpS). In comparison of the performance under similar complexity, our approach outperforms the baseline by ∼0.2dB to ∼0.25dB at the optimal transmit power, and ∼0.3dB to ∼0.45dB towards the more nonlinear region.