mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-05-08 02:28:25 -05:00
[GH-ISSUE #129] Need content on meta-learning and continual learning #3894
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/cs249r_book#3894
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @V0XNIHILI on GitHub (Dec 11, 2023).
Original GitHub issue: https://github.com/harvard-edge/cs249r_book/issues/129
Originally assigned to: @V0XNIHILI on GitHub.
As discussed in more detail in #106, there could be more focus on the use of meta-learning and continual learning methods for robust edge deployments. I can help write this. What would be a good 'location' to include such content? Maybe 7.5.4?
@profvjreddi commented on GitHub (Dec 11, 2023):
Thanks for offering to write it, really appreciate it!
Yea 7.5.4 is a good place though that chapter is starting to grow well beyond frameworks if we keep doing that. But for now let's get the content in and maybe in the future we can do a shuffle around
@V0XNIHILI commented on GitHub (Jan 4, 2024):
@profvjreddi I discussed with Charlotte about writing this section and she suggested me to first write the paper from my MSc thesis results and then write the book section(s) based on that, as some of the content from my background section could be use as a base for the text in the book. That would mean that I could contribute this part to the book around March. Would that work for the project?
@profvjreddi commented on GitHub (Jan 5, 2024):
Hi @V0XNIHILI sure that would work. Thanks!
@profvjreddi commented on GitHub (Apr 3, 2026):
This is a great topic but with the two volume restructure the scope has been tightened considerably. Volume I focuses on single machine ML systems foundations and Volume II focuses on distributed systems at scale. Meta learning and continual learning are important topics but they fall outside the core systems focus of both volumes. Closing this as out of scope for this edition. Thanks @V0XNIHILI for the suggestion way back when!