non-linear dimension reduction via Autoencoder

조회 수: 5 (최근 30일)
abassidodo
abassidodo 2017년 10월 5일
답변: Tommi Kärkkäinen 2022년 11월 9일
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?

답변 (2개)

BERGHOUT Tarek
BERGHOUT Tarek 2019년 4월 11일
1) try to normalize you data first, between 0 and 1.
2) use these autoencoders and tell me the difference

Tommi Kärkkäinen
Tommi Kärkkäinen 2022년 11월 9일

카테고리

Help CenterFile Exchange에서 Dimensionality Reduction and Feature Extraction에 대해 자세히 알아보기

Community Treasure Hunt

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

Start Hunting!

Translated by