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

10/10/2018
by   Deniz Mengu, et al.
0

In their Comment, Wei et al. (arXiv:1809.08360v1 [cs.LG]) claim that our original interpretation of Diffractive Deep Neural Networks (D2NN) represent a mischaracterization of the system due to linearity and passivity. In this Response, we detail how this mischaracterization claim is unwarranted and oblivious to several sections detailed in our original manuscript (Science, DOI: 10.1126/science.aat8084) that specifically introduced and discussed optical nonlinearities and reconfigurability of D2NNs, as part of our proposed framework to enhance its performance. To further refute the mischaracterization claim of Wei et al., we, once again, demonstrate the depth feature of optical D2NNs by showing that multiple diffractive layers operating collectively within a D2NN present additional degrees-of-freedom compared to a single diffractive layer to achieve better classification accuracy, as well as improved output signal contrast and diffraction efficiency as the number of diffractive layers increase, showing the deepness of a D2NN, and its inherent depth advantage for improved performance. In summary, the Comment by Wei et al. does not provide an amendment to the original teachings of our original manuscript, and all of our results, core conclusions and methodology of research reported in Science (DOI: 10.1126/science.aat8084) remain entirely valid.

READ FULL TEXT

page 1

page 2

page 3

page 4

09/22/2018

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

Lin et al. (Reports, 7 September 2018, p. 1004) reported a remarkable pr...
02/04/2020

A Deep Conditioning Treatment of Neural Networks

We study the role of depth in training randomly initialized overparamete...
04/30/2018

Machine Learning for Exam Triage

In this project, we extend the state-of-the-art CheXNet (Rajpurkar et al...
04/06/2021

Point classification with Runge-Kutta networks and feature space augmentation

In this paper we combine an approach based on Runge-Kutta Nets considere...
03/27/2019

Comment on "Conditional Decoupling of Quantum Information"

Berta et al [Phys. Rev. Lett., 121, 040504 (2018)] claim that their resu...
09/09/2021

SPLICE: A Synthetic Paid Loss and Incurred Cost Experience Simulator

In this paper, we first introduce a simulator of cases estimates of incu...
04/12/2022

Acacia-Bonsai: A Modern Implementation of Downset-Based LTL Realizability

We describe our implementation of downset-manipulating algorithms used t...