Course talk:CPSC522/Exploring Results of Conditional Generative Adversarial Networks with Self-Organizing Maps

From UBC Wiki
Jump to navigation Jump to search

Contents

Thread titleRepliesLast modified
Feedback015:32, 23 April 2020
Feedback005:46, 23 April 2020
Critique004:49, 23 April 2020
Feedback020:07, 22 April 2020

Interesting topic and well written, I found it a bit confusing to read the methodology after the experiment, I think reorganizing it might help your structuring. I also strugled a bit interpreting the heat maps, perhaps plaing them next to the image used to formulate it might make it more interpretable. Overall pretty good!

The topic is relevant for the course. 5 The writing is clear and the English is good. 5 The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds). 5 The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 4 The abstract is a concise and clear summary. 4 There were appropriate (original) examples that helped make the topic clear. 4 There was appropriate use of (pseudo-) code. It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). 5 It is correct. 5 It was neither too short nor too long for the topic. 5 It was an appropriate unit for a page. 5 It links to appropriate other pages in the wiki. 5 The references and links to external pages are well chosen. 5 I would recommend this page to someone who wanted to find out about the topic. 5 This page should be highlighted as an exemplary page for others to emulate. 4

If I was grading it out of 20, I would give it: 18

TommasoDAmico (talk)15:32, 23 April 2020

The frequency heatmaps were rather unintelligible, at least to me. Perhaps providing a separate interpretation for each individual heatmap would help clarify the purpose and the meaning. What would it mean to have more dark cells vs. fewer dark cells? How was the Jaccard index calculated for images? Was every image treated as a single cluster? What was the point of reporting this measure? The contents in the conclusion section could be broken down into limitations or future works. Perhaps providing a high-level summary of your findings as well as discussing whether these findings were in line with your expectations would be more fitting for this section. Overall, it was an excellent page.

P.S. The word similarity was misspelled as "similiarity" (almost everywhere)

The topic is relevant for the course. 5 The writing is clear and the English is good. 5 The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds). 5 The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 4 The abstract is a concise and clear summary. 5 There were appropriate (original) examples that helped make the topic clear. 4 There was appropriate use of (pseudo-) code. It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). 5 It is correct. 5 It was neither too short nor too long for the topic. 5 It was an appropriate unit for a page. 5 It links to appropriate other pages in the wiki. 5 The references and links to external pages are well chosen. 5 I would recommend this page to someone who wanted to find out about the topic. 5 This page should be highlighted as an exemplary page for others to emulate. 4

If I was grading it out of 20, I would give it: 19

AlirezaIranpour (talk)05:30, 23 April 2020

EXcellent paper all around! The only thing I would change, as Peyman suggested, is to create a future works section for the paper.

The topic is relevant for the course. 5 The writing is clear and the English is good. 5 The page is written at an appropriate level for CPSC 522 students. 5 The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 5 The abstract is a concise and clear summary. 5 There were appropriate (original) examples that helped make the topic clear.- There was appropriate use of (pseudo-) code. - It had a good coverage of representations, semantics, inference and learning. 5 It is correct. 5 It was neither too short nor too long for the topic. 5 It was an appropriate unit for a page. 5 It links to appropriate other pages in the wiki. 1 The references and links to external pages are well chosen. 5 I would recommend this page to someone who wanted to find out about the topic. 5 This page should be highlighted as an exemplary page for others to emulate. 5 If I was grading it out of 20, I would give it: 19

ObadaAlhumsi (talk)04:49, 23 April 2020

This a great page with lots of details in every section. I found it a bit awkward to read about the experimental setting before the method but I guess that's unique and not really problematic. The work finishes off by saying there are still unanswered questions. This can be turned in an excellent future works discussion but seems to have been left rather under explored. All and all said, however, an excellent page. Overall grade: 19/20

PeymanBateni (talk)20:07, 22 April 2020