Letter to Reviewer 3
Major: Submission readability While the submission is readable and the main ideas are accurately presented, it suffers from pervasive grammatical errors and uncommon word choices that negatively impact the communication of the research. This is my primary concern with the submission. The research here is interesting and I am excited to see it eventually published, but as is, it needs multiple rounds of prose iteration and improvement to meet academic publishing standards (Distill, or any other computer science conference).
Thank you for the comment. We made a full pass of our article and tried our best to eliminate such errors.
Major: Grand Tour technique introduction Given the emphasis on the Grand Tour technique, which is an interesting perspective on visualizing neural network activations, there is likely a better way to introduce and frame the technique with respect to modern techniques. Specifically, the phrase “somewhat-forgotten” feels self-defeating and could be improved to excite the reader about this technique. Furthermore, for readers that may not know of it, was it somewhat-forgotten for good reason? Or did it simply fall out of research popularity? Some discussion around this may be helpful to properly situate the technique in history.
Thank you for the comment. We changed it to “under-appreciated” to clarify our stand.
Major: Better presentation of technical details The technical details section would be better placed in the acknowledgements of the article. However, since it is quite long (somewhere between 1/4 and 1/3 of the article), another idea is that it could be highlighted with a banner description and hidden by default with an indicator to reveal upon a reader interaction (e.g., show/hide button).
Thank you for the suggestion. Now we hide the technical details by default.
“Minor: Hero / banner interactive graphic While the top-level graphic is eye-catching and hints at the techniques used in the paper, perhaps a caption and light annotation could help improve its message to readers. This would help push it towards substantial preview of the article, rather than only a nice looking animation.”
Thank you for the suggestion. We added a caption with clickable texts to the banner image.
Minor: Broken graphic The Grand Tour of the softmax layer” figure was broken: the image/points drop down menu did not update the visualization correctly, nor did the data instance positions did not update.
Thank you for the comment. We fixed this bug caused by uncaught “onscreen” events (e.g. when scrolling too fast).
Capitalize headings?
Thank you for the comment. We capitalized the headings.
“The math behind the two is simple.” Be careful with phrases such as these, since readers will come from many diverse backgrounds with different levels of mathematical fluency.
Thank you for the suggestion. We made a full pass of our article and removed such phrases.
Adding a zoom slider to all Grand Tour visualizations (not just the later ones) could be useful
Thank you for the suggestion. We added zoom sliders to all Grand Tour visualizations.
“vis” instead of “visualization”, although explicitly indicated in the submission, reads a bit informal
Thank you for the comment. We made a full pass and replaced every “vis” to “visualization”.
While there could be other citations to include to support the first paragraph of the introduction (e.g., work related to visualization and visual analytics in deep learning, neural network interpretability), the current text passes.
Thank you for the comment.
In the Discussion, I expected to see citations or relevant links/materials to corroborate “The trade-offs between small multiples and animations is an ongoing discussion in the vis community.”
Thank you for the comment. With citations, we clarified the limitations and challenges in comparative studies of small multiples and animations in the ”The Power of Animation and Direct Manipulation” section.