non-linear dimension reduction via Autoencoder

6 次查看（过去 30 天）

显示更早的评论

abassidodo 2017-10-5

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/359742-non-linear-dimension-reduction-via-autoencoder

回答： Tommi Kärkkäinen 2022-11-9

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 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

回答（2 个）

BERGHOUT Tarek 2019-4-11

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/359742-non-linear-dimension-reduction-via-autoencoder#answer_370194

1) try to normalize you data first, between 0 and 1.

2) use these autoencoders and tell me the difference

https://www.mathworks.com/matlabcentral/fileexchange/66080-auto-encoder-based-extreme-learning-machine?s_tid=prof_contriblnk

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Tommi Kärkkäinen 2022-11-9

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/359742-non-linear-dimension-reduction-via-autoencoder#answer_1095413

You might try this also:

https://se.mathworks.com/matlabcentral/fileexchange/119043-additiveautoencoder?s_tid=prof_contriblnk

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

类别

AI and Statistics Deep Learning Toolbox Train Deep Neural Networks Function Approximation, Clustering, and Control Function Approximation and Clustering Pattern Recognition

在 Help Center 和 File Exchange 中查找有关 Pattern Recognition 的更多信息

标签

Community Treasure Hunt

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

Translated by