How to reduce dimension before using logistic regression?

I am doing an MNIST handwritten digits recognition with logitic regression.But I found using 784 dimensions is too much. Is it possible to reduce the dimension before doing logistic regression like using PCA or LDA?

回答(0 个)

类别

帮助中心File Exchange 中查找有关 Statistics and Machine Learning Toolbox 的更多信息

Community Treasure Hunt

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

Start Hunting!

Translated by