Project 2 - John Marcao #20
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
…and verified matrix multiplcation via cuBLAS library.
…o several smaller kernels and store intermediate values in arrays.
This reverts commit f1e5d9b.
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Outdated suggestions cannot be applied.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.
Extra Day 1 of 4 used for this project!!!
Repo Link
Part 1) Stream Compaction
Implemented all requirements, did performance analysis. Did not do extra credit.
Part 2) Character Recognition
Implemented Perceptron, but was not able to resolve all bugs with backpropagation in time. My own fault, but time was incredibly tight. Forward propagation works with some caveats.
Thoughts
Even though I didn't finish the Character Recognition project, I still think its enjoyable and very interesting, if a little frustrating. However, the instructions are lacking. There are no requirements and its easy to get thrown down a rabbit-hole of different implementations. I think this project would benefit from having clearly defined requirements and some more skeleton code. Maybe having skeletons for the steps of Back-Propagation with no implementation inside.
(I may try to fix the perceptron before midnight of 9/18 to secure the project)