Skip to content

Latest commit

 

History

History
11 lines (9 loc) · 487 Bytes

README.md

File metadata and controls

11 lines (9 loc) · 487 Bytes

SVM Classifier with a Convolutional Autoencoder for Feature Extraction

Software

Python3
Tensorflow-gpu
Matplotlib
Numpy
Sklearn

Description

A convolutional autoencoder was trained for data pre-processing; dimension reduction and feature extraction. Additionally, an SVM was trained for image classification and attached to the central layer of the network. Essentially, MNIST data is fed into the autoencoder, which then feeds the result into the SVM for classification.