All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Please revise the paper according to the comments, Thank you.
[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. It is a common mistake to address reviewer questions in the rebuttal letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the rebuttal letter. Directions on how to prepare a rebuttal letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
[# PeerJ Staff Note: The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at firstname.lastname@example.org for pricing (be sure to provide your manuscript number and title) #]
The article must be written in English and must use clear, unambiguous, technically correct text. The article must conform to professional standards of courtesy and expression.
The investigation must have been conducted rigorously and to a high technical standard. The research must have been conducted in conformity with the prevailing ethical standards in the field.
The conclusions should be appropriately stated, should be connected to the original question investigated, and should be limited to those supported by the results. In particular, claims of a causative relationship should be supported by a well-controlled experimental intervention. Correlation is not causation.
This paper is totally well written easy to understand because the authors did a good conclusion on the part of basic concepts. This manuscript mainly researches several questions such as developments of SC CNN and how does it compute etc. Thus, authors must be concerned about some details as follows:
1. I suggest the authors attach all the figures and place them around the appropriate paragraph respectively in the manuscript as much as possible. Anyway, authors must improve the quality for all the figures, font size must be adjusted and unified, the resolution must be improved. If all the figures are quoting, authors must indicate references respectively.
2. This manuscript has too many abbreviations and parameters. Therefore, if necessary, I suggest authors should list a nomenclature table with its name, unit of measurement, and description of all variables (explanation) at the beginning of this manuscript.
3. In the Basic Concepts section, some algorithms and methods such as logical formulas should be more concise. Some expressions should be modified to the mathematical mode when using exponential computing, for instance, 2n, instead of 2^n.
4. Related work is not enough in this paper, authors should quote the latest references (2019-2020). In addition, this manuscript is weak in part of the conclusion. It will be better if authors make a summary and extension for each research work in "SC implementation in CNN's".
5. What are the development prospects of the SC CNN algorithm? And how did other relevant researchers prepare to process the open problems? By the way, the author's personal views throughout this paper are quite weak, this section must be restructured and polished.
6. Because of the development of CNN architectures, various models based on CNN such as ImageNet and googLeNet etc. Authors need to compare the performance variation between state-of-the-art CNN architectures and traditional CNN during SC Implementation.
This submission reviews the key concepts of Stochastic computing (SC) and the circuit structure and then compare the advantages and disadvantages amongst different methods. Finally, This submission concludes the overview of SC in CNN and make suggestions
for widespread implementation in the near future.
This submission is within the scope of the journal
This is a review without technical novelty.
This submission is with good discussions.
English writing should be improved in this manuscript.
This review article introduces stochastic computing and deep learning, especially CNN based SC methods. This is quite helpful for these researchers in this field.
1, English writing should be improved. Some statistical results should be shown in tables instead of sentences.
2, More recent researches should be introduced for better description.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.