Skip to content

A feature extractor based on Python 3, Tensorflow, and Scikit-learn created to improve the SVM accuracy to classify the MNIST dataset fast and with more accuracy.

License

Notifications You must be signed in to change notification settings

dlmacedo/SVM-CNN

Repository files navigation

SVM-CNN

It is my project based on Python 3, Tensorflow, and Scikit-learn for the course Hybrid Systems of Center of Informatics of UFPE (2016.1). This course is related to my Master's Degree in Deep Learning. The idea is to extract features from the MNIST dataset and then use SVM to classify their images. We show that it improves the accuracy compared to the regular CNN and is faster than ELM of worst accuracy.

To run it, you should type:

python main.py

About

A feature extractor based on Python 3, Tensorflow, and Scikit-learn created to improve the SVM accuracy to classify the MNIST dataset fast and with more accuracy.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages