Batch version of 3 layer neural network has been implemented using CUDA in C++. The weight updates of the nodes in each layer in forward and back propagation have been parallelized to reduce the main overhead of batch update. The model predicts cat vs non cat images. The network takes flattened image matrices as input. The dataset used is CIFAR-10 and preprocessing has been done using python.
-
Notifications
You must be signed in to change notification settings - Fork 2
Batch version of 3 layer neural network implemented using CUDA in C++
License
rnjtsh/Neural-Network-using-CUDA
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Batch version of 3 layer neural network implemented using CUDA in C++
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published