Project 2: Caroline Lachanski #24
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Repo link
Implemented various implementations of scan and stream compaction
Implemented all code for character recognition
XOR example seems to work, actual character recognition seems to have issues with back propagation
I tried very very hard (and almost destroyed my repo in the process) to push my weights file for character recognition but it was too large (if you need it I have it and can send it another way)
Feedback on project: This project (really two projects) was an insane amount of work, especially for someone who's never done machine learning. At the very least, the readme could have been a little more descriptive about how back propagation works, or provide tips on how to organize/pass around data and create kernels for the process. Additionally, it was frustrating to later see stream compaction elevated to the more important assignment, especially after we were told to finish it quickly and spend more time on character recognition. I would have liked to have more spent more time actually optimizing my scan and stream compaction code and doing extra credit, rather than rushing through two assignments.