Feedback

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