PROJECT2: SOMANSHU AGARWAL #6
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
|
Merging the changes. |
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Outdated suggestions cannot be applied.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
The project was divided into two sub projects:
Stream Compaction: The motive in the project was to analyze the Naive, Work-Efficient and Thrust implementations in GPU and compare the run time with serialized CPU and make the analysis. I analyzed the performance with varying block size and input array and made inferences on the bottlenecks of the algorithms and reasoning behind it.
Character Recognition: The motive was to train a Neural Network that would train on the given data set and recognize the alphabets of the given classes. We first train and check the Neural network on XOR inputs and output and then check on the character recognition. The weights of the arrays, soft max probabilities and the hidden layer unit values are provided in the .txt files. Also, loss vs iterations plots are given for analysis.