non-linear dimension reduction via Autoencoder
4 ビュー (過去 30 日間)
古いコメントを表示
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?
0 件のコメント
回答 (2 件)
BERGHOUT Tarek
2019 年 4 月 11 日
1) try to normalize you data first, between 0 and 1.
2) use these autoencoders and tell me the difference
0 件のコメント
参考
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!