Course talk:CPSC522/Alternative Classifiers

Overall the page is well written and the topic is very interesting. The abstract is quite long; this version could be used as introduction (since it’s missing) in the Content section, and a shorter version should be used as Abstract. The page is also missing the short one-sentence summary that helps the reader grasp the topic. The theoretic background for the topic is quite advanced and I think it’s not a base knowledge for CPSC 522 students. For this reason I think the page would benefit from either a bit more explanation on core topics or proper references for these.

The topic is relevant for the course. 5 The writing is clear and the English is good. 4 The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds). 4 The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 4 The abstract is a concise and clear summary. 3 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: 17.5

The topic is interesting and movel to explore from my understanding. Although I believe the use of language may be slightly advanced for this course, further explaining certain core concepts might help the readability of the page. Otherwise I think the page looks good, great choice.

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). 4 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. 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

The page is rich with technical details that overshadow the objectives of the project and the bigger picture. Perhaps you could consider a section to elaborate on your motivations. What makes these alternative classifiers special and distinct from the current one? Does linear classification have any particular limitations that you were trying to address other than room for improved accuracy? What is the difference between scratch and pretrained in the initialization? It appears that the Euclidean Classifier improved the accuracy only when the initialization was scratch. Is there a reason for that? The improvements do not seem significant (maybe you could conduct statistical tests to investigate that). Given the marginality of the improvements, why would we be interested in these classifiers? How did these classifiers compare in terms of speed? Why were the results NA for the Mahalanobis Classifier for CIFAR100? Also, in your future work section, you could provide some evidence or motivation as to why we should investigate end-to-end learning of covariance-based classifiers (maybe indicate the potential benefits). All things considered; it was a really good page.

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). 4 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

I think the page is extremely well written and concise (as usual). I only have 2 comments for the page. Firstly, the abstract section felt like an introduction section, while I think separating the sections will force the page to be longer as some ideas will have to be reiterated, you can try writting a small abstract like "This page will explore alternative classifiers for CNNS" and make your current abstract into an introduction.

Secondly, I think the future work section will be better with more concrete ideas of what can be done next.

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. 3 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. 4.5 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. 5 If I was grading it out of 20, I would give it: 19

The abstract starts with mentioning "visual classification", it is not very clear to me what exactly that means and how different it is from regular classification if at all? I think you could also shorten the abstract to focus more on the main ideas/experiment points, the middle of the abstract sounds like it more belongs to an Introduction section. There are some spaces missing after inserted maths throughout the page. There is a typo of "unforunately" in the Laplacian classifier section. Also "the use of the absolute differeNT in the Laplacian classifier"

After reading the page I am still not sure on the motivation of why we would want to consider alternative classifiers? I guess this got somewhat lost for me amongst the technical details. I would suggest to add an introductions section that takes the details that are covered in the abstract and uses more simple language to hammer down the point in layman terms about the motivation.

The topic is relevant for the course. 5 The writing is clear and the English is good. 4 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. 3 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. 4 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