non-linear dimension reduction via Autoencoder

5 views (last 30 days)
hello all, I am trying to use the Matlab implementation of autoencoder to reduce the dimension of 1509 samples of Bag-of-visual word models of images, but I am surprised that while the image classification without dimension reduction recorded about 50% accuracy, and Matlab's PCA improved it to 60% but the Matlab implementation of autoencoder (with logsig activation and default values for all the parameters) reduced it to 40%. I expect higher accuracy from autoencoder, what can be the problem?

Answers (2)

BERGHOUT Tarek
BERGHOUT Tarek on 11 Apr 2019
1) try to normalize you data first, between 0 and 1.
2) use these autoencoders and tell me the difference

Tommi Kärkkäinen
Tommi Kärkkäinen on 9 Nov 2022

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!