Optical neural networks promise unmatched efficiency, bandwidth, and latency, critical benefits as demand for neural network hardware surges. However, their practical value for general-purpose acceleration or specialized applications must be proven under application-realistic conditions. We discuss recent insights and outline key research priorities.
@article{arxiv.2605.18178,
title = {The thin line for optical neural networks towards broad practical relevance},
author = {Anas Skalli and Daniel Brunner},
journal= {arXiv preprint arXiv:2605.18178},
year = {2026}
}