"$d_PROJECTS"'My Reviews/1_Paper_Review_form.txt' # www.BillHowell.ca 26Jan2018 updated from a long series of iterations over the years To automatically move comments from the "DETAILS" section to other sections, see # loaddefs "$d_Qndfs"'review move comments.ndf' +-----+ Neural Networks Paper Reviews http://ees.elsevier.com/neunet/ NN journal accepts greek letters, eg : α β γ δ ε ζ η θ ι κ λ μ ν ξ ο π ρ ς σ τ υ φ χ ψ ω EasyChair does, too. Paper : Assigned : Due : For each question, please use the following scale to answer (place an X in the space provided): RATINGS 1 Superior 2 Good 3 Fair 4 poor 5 Not applicable Quality of Methodology : Quality of Work : Soundness of Conclusions : Significance of Subject : Clarity : Organization : Priority Rating for Publishing in Neural Networks ("1" is highest) : Is the abstract, and are the figures, legends, and references acceptable? If not please explain: Please provide a brief and compelling argument supporting (a) your recommendations and (b) the above ratings: >> See my comments to the authors. +-----+ IJCNN Paper Reviews (As per IEEE-CIS formatting style) IEEE-CIS system does NOT accept greek letters : α β γ δ ε ζ η θ ι κ λ μ ν ξ ο π ρ ς σ τ υ φ χ ψ ω EasyChair does, too. Copy my comment section to authors : From : review writeup To : /media/bill/HOWELL_BASE/Qnial/MY_NDFS/paper reviews - raw review.in Run QNial "clean-up" : IEEE and others : "$d_Qndfs"'paper reviews - strip out illegal characters.ndf' Paper : Assigned : Due : Relevance to the conference: Rate the relevance of the topic addressed in the paper within its area of research. Excellent Good Acceptable Little None Technical content and scientific rigour: Rate the technical content of the paper (e.g.: completeness of the analysis or simulation study, thoroughness of the treatise, accuracy of the models, etc.), its soundness and scientific rigour. x Excellent work and outstanding technical content. Solid work of notable importance. Valid work but limited contribution. Marginal work and simple contribution. Some flaws. Questionable work with severe flaws. Quality of presentation: Rate the paper organization, the clearness of text and figures, the completeness and accuracy of references. x Excellent. Well written. Readable, but revision is needed in some parts. Substantial revision work is needed. Unacceptable. Novelty and originality: Rate the novelty and originality of the ideas or results presented in the paper. A pioneering piece of work. Striking novel ideas or results. x Significant original work and novel results. Some interesting ideas and results on a subject well investigated. Minor variations on a well investigated subject. It has been said many times before. Overall Rating: Do you recommend acceptance or rejection of this paper? x Strongly Accepted Accepted Neutral Rejected Strongly Rejected Best Paper: Should the paper be considered for best paper awards? x No Yes SS, tutorials,workshop: Evaluation x Accepted Maybe Rejected Comments for Authors: Please describe in detail main paper contributions, positive aspects, observed deficiencies, and suggestions on how to improve them: Confidential Comments for Conference Committee Use Only: Committee members will be able to see both the comments to authors AND the comments to committee members +-----+ ISNN & ICIST Paper Reviews (As per EasyChair formatting style) 09Feb2018 EasyChair system accepts greek letters : α β γ δ ε ζ η θ ι κ λ μ ν ξ ο π ρ ς σ τ υ φ χ ψ ω but NOT Unicode Paper : Assigned : Due : Overall evaluation : Scale : 3 strong accept, 2 Accept, 1 Weak accept, 0 Neutral, -1 Weak reject, -2 Reject, -3 Strong reject Reviewer's confidence : Scale : 5: (expert), 4: (high), 3: (medium), 2: (low), 1: (none) Please provide a detailed review, including a justification for your scores. Both the score and the review text are required. +-----+ Neural Computing & Applications - Paper Review http://nca.edmgr.com/ https://link.springer.com/journal/521 Paper : Assigned : Due : Note that the rating system for Neural Networks journal, plus my own personal approach, have been blended with NCA guidelines for this review. For each question, please use the following scale to answer (place an X in the space provided): RATINGS 0 - Out of Scope of the Journal 2 - Unsatisfactory or has major weaknesses 4 - Has merit but needs work 6 - Good 8 - Excellent 10 - Outstanding Overall Score : ? Accuracy : ? Novelty, timeliness : ? Relevance to the NCA : ? (theory, not for practical applications techniques) References : ? Readable, interesting, timely: ? Figures and tables : ? For the criteria above, definitions and selected comments are provided below. However, most comments are provided in the "reviewer's personal approach" in a later section below. Description of criteria by NCA : Accuracy, math Is the paper accurate? Are there any important errors in the mathematics or scientific precepts? Novelty: Is the work novel? Assessing novelty is difficult, but your opinion on this would be useful. If you have any doubts at all, and would like to ask the author any questions relating to their paper, please indicate the questions in your response to the Editor who will communicate with the authors on your behalf. If you feel that you would like to discuss the paper with close colleagues, please do so, stressing the confidential nature of the discussion. Relevance to the NCA: Applications techniques Does the paper demonstrate the application of the techniques described using either simulated or real world problems? Note that papers which are entirely theoretical and do not address applications (simulated or real) should be scored as 0 = Out of Scope of the Journal. References: should be relevant and some of them should be fairly recent. Are any important references of which the authors should be aware excluded? Readable, interesting, timely: Is the paper readable, interesting and timely; do the results follow from the data obtained, and are the arguments clear and logical. Even if the topic is not directly in your field, what are your impressions? Do not be too concerned about the standard of English used in the paper, unless it makes the understanding of the paper difficult. Figures and tables : Do the figures and tables enhance the arguments and are they clear and supportive to the text? Does the text explain the diagrams and tables in the context of the overall argument? Is the paper well presented? Comments As a guide, most reviewers submit around a half page of comments on papers they review. A summary of comments will be send to the authors, unless reviewers put comments directly on the manuscript. Comments can be returned to the Editor by post, e-mail, fax or telephone - see the Editor's contact details. See details below, including requested changes. ********************************************** SUMMARY COMMENTS III ++---------------------------++ This reviewer's personal approach, nomenclature examples: p1c1h0.8 = means page 1, column 1 ~80% of the way down the [text, image]s on the page C2. = means section "C2. WEAKNESSES:" of this review uses a physical ruler in front of computer screen to read height-on-page, QNial to calc fraction eg frac IS OP hPosn { (hPosn - 16.2) / (42.8 - 16.2) } [42.8, 16.2, hPosn] cm = [bottom, top, pointOfInterest] of text "inline" notations (no special formatting) : d[dt: ...] = normal derivative; dp[dx: ...] = partial derivative l_or_ij(s) - means an overscore on l, for l(i,j,s) IEEE-only review submissions substitutes for illegal characters that are not accepted : (- = longer hyphen) (" = left & right quotes) other illegal characters are discarded geany text editor regexpr search : <([^ ]) replace : < \1 EDAS review submissions substitutes for illegal characters that are not accepted : `< character needs following space, eg : < tild> < num> < pwr> < and> < at> < vertBar> view this file in constant width font (eg Liberation Mono 10 point) and tab = 3 spaces ++---------------------------++ ACTIONS REQUESTED OF THE AUTHORS I have no critical changes to request of the authors. RRR NOTE: Actions by the authors are NOT required for the points listed in the rest of my review below. I am very afraid that authors feel that they are obliged to answer or make changes, which could waste far too much of their time, and several of my comments may be speculative and may not even be correct! *************************** *************************** COMMENTS ONLY - actions by the authors are NOT required for the points listed below, to the end of the review. Perhaps some of these comments will be helpful in some way. (Main paper contributions, positive aspects, observed deficiencies, and suggestions on how to improve them:) +!!!!!!!!!!!!!!!+ WARNING : The following paragraphs are several different comments that may be applicable to the paper being reviewed. If you can see this message, then I forgot to customize the comments, and this sub-section should be ignored. PERTINENCE of the paper for the "Neural Networks" journal : As per the Aims and Scope" listed on the copyright page of each issue of the journal : "... Neural Networks welcomes high quality submissions that contribute to the full range of neural networks research, from behavioral and brain modeling, learning algorithms, through mathematical and computational analysis, to engineering and technological applications of systems that significantly use neural network concepts and techniques. ..." PERTINENCE of the paper for IJCNN2015 Killarney, Ireland : As per the "Call for Papers" listed at http://www.ijcnn.org/call-for-papers : "... IJCNN 2015: The annual International Joint Conference on Neural Networks (IJCNN) is the flagship conference of the IEEE Computational Intelligence Society and the International Neural Network Society. It covers a wide range of topics in the field of neural networks, from biological neural network modeling to artificial neural computation. ..." The current paper does not develop or assess a technique for neural network learning or evolving, nor for the application of neural networks, so it is off of the main themes of the IJCNN, as I understand it. That is the main reason that I gave this paper a weak rejection. That should NOT be taken as a critique of the paper itself! PERTINENCE of the paper for the "Neural Computing & Applications" journal : As per the "About this journal" section of the home page of the journal, http://www.springer.com/computer/ai/journal/521/PS2 : "... Neural Computing & Applications is an international journal which publishes original research and other information in the field of practical applications of neural computing and related techniques such as genetic algorithms, fuzzy logic and neuro-fuzzy systems. ... Presents new and significant research, developments and applications of practical use and value. ... Covers all items relevant to building practical systems ..." However, effective non-NN toolsets are often a key basis or foundation for later work with neural networks, and they can provide an important context for NN work. But that judgment is really up to the review and program chairs, who may have reasons that I am not aware of for including this topic on the program. PERTINENCE of the paper for ICIST International Conference on Information Science and Technology : As per the "Topic Areas" listed at https://conference.cs.cityu.edu.hk/icist/ : "... ICIST 2019 aims to provide a high-level international forum for scientists, engineers, and educators to present the state of the art of research and applications in related fields. ..." Fields : Computer Science and Engineering, Control and Automation, Signal Processing and Telecommunications, Bioinformatics and Biomedical Engineering (see detailed topics for each area) +!!!!!!!!!!!!!!!+ ++---------------------------++ C0. SPECIAL SECTION: COMMENTS FROM AN EXPERT IN THE AREA (if applicable to this review) ++---------------------------++ C1. STRENGTHS OF THE PAPER: SSS ++---------------------------++ C2. WEAKNESSES: (again, changes to the paper are not require for these comments) WWW ++---------------------------++ C3. QUESTIONS and COMMENTS: (no need to answer) QQQ +-----+ COMMENTS: CCC ++---------------------------++ C4. DETAILS and GRAMMAR: (again, changes to the paper are not required for these suggestions) +!!!!!!!!!!!!!!!+ WARNING : The following paragraphs are several different comments that may be applicable to the paper being reviewed. If you can see this message, then I forgot to customize the comments, and this sub-section should be ignored. This paper is well written and is easily understood, so I only have a few suggestions to make. These tend to be stylistic, and may not be better than the authors' original version, so they should only be considered if to the authors' liking. This paper is written in a manner that is easily understood, with perhaps the occasional grammatical glitch, so I have made a few suggestions. These tend to be stylistic, and may not be better than the authors' original version, so they should only be considered if to the authors' liking. This paper is written in a manner that can be understood, with perhaps the occasional sentence structure complication or grammatical glitch. With journal papers I make an attempt to help with at least some of the wording, but given conference paper deadlines and given that there aren't serious problems with the grammar of this paper, I have made only a few suggestions for changes. These tend to be stylistic, and may not be better than the authors' original version, so they should only be considered if to the authors' liking. Although the meaning of the authors' writing is for the most part understandable with some effort on the readers part, there are many phrases and sentences are written in a manner that makes it difficult to follow the material. I would - shortening some long sentences, with the intent to force a more clear, concise phrasing. - adding clarifying remarks in some phrases, as it isn't always clear which point is being alluded to - verb tenses are sometimes mixed up I have made several suggestions for changes, which may have introduced errors and mis-interpretations, so the authors should decide if my suggestions are appropriate or not. There are many spelling and grammatical mistakes that could have been picked up with a spell-checker or grammar-checker, so I have not suggested changes for these. The authors should correct the spelling, and use a grammar check as well. Note that most of the spelling mistakes appear [in the first two pages, p9], whereas the grammatical errors are distributed throughout the paper. Some general suggestions are : - [singular, plural, past, present] forms of words should be consitent with the rest of the sentence - the past tense should be used for what was done, the present tense to state 'ideas or principles that continue to be considered - [could, would] versus [can, will] - the authors are cautious in often using the conditional [could, would] forms, but common practice is to favour the definitive forms [can, will]. But at least use the same form in adjacent [phrases, sentences, paragraphs] where "the same form should apply" (most of the time, but not always, for example, when you do want to make a distinction). - Articles [the, a, etc] are sometimes required, and sometimes not - this must be a confusing part of English. - don't start sentences with "and" - capitalize the first letter of authors' names!! - pay attention to [singular,plural] as this causes much confusion in your paper - beware of [complex, convoluted] sentences, as sometimes these are best simplified where possible for clarity. - selection of prepositions like [of,for,with,to,...etc] is problematic, and articles [the, a, etc] are sometimes required, and sometimes not - these must be a confusing part of English. +!!!!!!!!!!!!!!!+ pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> pch0. change to "... ..." >> ++---------------------------++ C5. REFERENCES (using a quick web search, as opposed to checks using Scopus or standard indexes.) I do not have access to CrossRefs "CrossCheck" via Elsevier's "iThenticate", but I assume that this is done by the editorial board. C5a) Are references and citations in the standard format? +-----+ Neural Networks journal example : Chun, M., Biglou, J., Lenard, J., & Kim, J. (1999). Using neural networks to predict parameters in the hot working of aluminum alloys. Journal of Materials Processing Technology, vol. 86, pp. 245-251 ... - indicates italicized lettering - References in standard format >> - Italicize the name of the publication (journal). >> - Vol(number) can be as "9(10)", for example. >> - References should be sorted by the first author's last name. >> - Citations in the text are of the form "... Chun, Biglou, Lenard, & Kim, 1999 ..." or "... Chun et al. 1999 ..." (not as reference numbers) >> +-----+ IJCNN example (IEEE-CIS standard) : [ISNN example (IEEE-CIS standard) : [27] F. Akopyan, J. Sawada, A. Cassidy, R. Alvarez-Icaza, J. Arthur, P. Merolla, N. Imam, Y. Nakamura, P. Datta, G.-J. Nam et al., “Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 34, no. 10, pp.1537–1557, 2015. ... - indicates italicized lettering (Publication name) - References in standard format >> - References should be sorted by numerical order (= order of citation) >> - Citations in the text are of the form "... [7] ..." (where 7 is the reference number) >> - Citations are numbered by order of appearance in the text. >> +-----+ [ISNN, ICICIP, ICIST] example : [27] F. Akopyan, J. Sawada, A. Cassidy, R. Alvarez-Icaza, J. Arthur, P. Merolla, N. Imam, Y. Nakamura, P. Datta, G.-J. Nam et al., “Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 34, no. 10, pp.1537–1557, 2015. ... - indicates italicized lettering - References in standard format >> - References should be sorted by numerical order (= order of citation) >> - Citations in the text are of the form "... [7] ..." (where 7 is the reference number) >> - Citations are numbered by order of appearance in the text. >> +-----+ Neural Computing and Applications journal example : 7. M. A. Cohen, and S. Grossberg. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. Syst., Man, Cybern., Vol. 13, No. 15, pp. 815-821, 1983. - References in standard format >> - References should be sorted by numerical order (= order of citation) >> - Citations in the text are of the form of reference numbers >> - Citations are numbered by order of appearance in the text. >> +-----+ C5b) Check a few reference details, and if they are legitimate (using a quick web search and personal familiarity with references)? >> By assuming that the editorial board uses iThenticate or tools like that, I no longer do this check. +--+ C5c) Is this paper significantly different from previous papers by the same authors? >> ???Yes No??? $ sed "Barchi\|Parisi\|Zanatta\|Bartolini\|Acquaviva" "$d_PROJECTS"'My Reviews/NCAA-D-23-07231 b Barchi etal: Energy Efficient and Low-latency SNNs, Embedded, Spiking Activity Tuning.txt' C5d) Is this paper novel with respect to the literature? >> To answer (C5[c,d]), I performed web searches +--+ C5e) Is the relevant literature well represented in breadth and Depth? >> ???Yes No??? - ************************** C6. MATH CHECKS - step-by-step +!!!!!!!!!!!!!!!+ Reviewer notes from the author's paper, plus any math checks, are provided in the file : http://www.BillHowell.ca/Neural nets/Paper reviews/ paper review- math only.txt !!!!!!!!!!!!!!!! ************************** C7. LIMITATIONS OF THIS REVIEW Reviewer's expertise on the subject: Low NNN http://www.BillHowell.ca/home.html ([webPages, internal links] are continually being revamped, many don't work) *************************** C8. THOUGHTS: (again, changes to the paper are not required for these - in fact changes SHOULD NOT be made!) Here are some long-winded thoughts that are not really relevant to the paper review per se... For interest only, even if that. These are separated from the "COMMENTS" above because they are less relevant to the actual paper. *************************** CONFIDENTIAL COMMENTS for review chair / committee use only: None other than the list of Ratings enddoc