Peer-Review Record
Latent-Insensitive Autoencoders for Anomaly Detection
Mathematics 2022, 10(1), 112; https://doi.org/10.3390/math10010112
Reviewer 1:
Anonymous
Reviewer 2:
Anonymous
Mathematics 2022, 10(1), 112; https://doi.org/10.3390/math10010112
Submission received: 14 November 2021
/
Revised: 8 December 2021
/
Accepted: 21 December 2021
/
Published: 30 December 2021
(This article belongs to the Collection Multiscale Computation and Machine Learning)
Round 1
Reviewer 1 Report
Please see that attached pdf for comment.
Comments for author File: 
Comments.pdf
Author Response
The responses are included in the attached file.
Author Response File: Author Response.pdf
Reviewer 2 Report
This paper presents a very interesting method for improving anomaly detection.
The manuscript is well organized, and the theoretical basics are carefully depicted.
Adding some clarifications would be advisable:
- A clear statement of the problem to solve in the abstract.
- Enumeration of the contributions in the “Introduction” section.
- Rephrase clearer the sentence: “ To prevent autoencoders… … of the input x. In Section 3.1.
- Add a reference to the Eckart-Young low-rank approximation theorem, in Section 4.1.
Authors should correct some typos:
- Upper case in “autoencoders” in line 51.
- "Activatin" in line 115
Author Response
The responses are attached.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The revised manuscript improved enough to be published in Mathematics.
