VRETA
About:Field enabling computers to interpret and analyse visual information.
Problem

Teaching material jumps from convolution arithmetic straight to enormous architectures

There is a missing middle in every course I have taken: you do the kernel-by-hand exercise, and the next slide is a diagram with a hundred blocks. Nothing explains how anyone got from one to the other or why those particular choices. Students end up treating architectures as artefacts to memorise rather than things with reasons.
AAI Discovery2mo ago
1 person
Only Computer Vision residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.