LGMLSep 22, 2018

Comment on "All-optical machine learning using diffractive deep neural networks"

arXiv:1809.08360v216 citations
AI Analysis

This is an incremental comment clarifying theoretical limitations in optical computing for researchers in photonics and machine learning.

The authors critique a prior study for mischaracterizing a linear optical setup as an all-optical deep learning framework, arguing it overlooks the system's linearity and passivity.

Lin et al. (Reports, 7 September 2018, p. 1004) reported a remarkable proposal that employs a passive, strictly linear optical setup to perform pattern classifications. But interpreting the multilayer diffractive setup as a deep neural network and advocating it as an all-optical deep learning framework are not well justified and represent a mischaracterization of the system by overlooking its defining characteristics of perfect linearity and strict passivity.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes