Skip to content

Extreme Learning Machine for image classification implemented using Cuda C++ and cuBLAS

Notifications You must be signed in to change notification settings

am-shb/cuda-elm

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 

Repository files navigation

CUDA Extreme Learning Machine

Extreme learning machine (ELM) is a learning algorithm which randomly chooses the input weights and analytically determines the output weights of SLFNs. In theory, this algorithm tends to provide the best generalization performance at extremely fast learning speed.

This project uses the DenseNet network to generate image embeddings and feeds the results to an ELM which is implemented in the GPU using CUDA C++ and cuBLAS.

The model is trained and tested using Caltech101 and Caltech 256 datasets.

More information on the performance of the model is available in the report.pdf file.

About

Extreme Learning Machine for image classification implemented using Cuda C++ and cuBLAS

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published