2016/04/26 · The proposed HSAE can well preserve the local geometry with Hessian regularization and performance robustly to noise with sparse constraint.
A semi-supervised auto-encoder using label and sparse regularizations for classification · Computer Science. Appl. Soft Comput. · 2019.
The advantages of it are twofold: (1) it adopts Hessian regularization to preserve local geometry of data points and (2) it also efficiently extracts the hidden ...
2016/04/26 · In this paper, we incorporate both Hessian regularization and sparsity constraints into auto-encoders and then propose a new auto-encoder ...
In this paper, we incorporate both Hessian regularization and sparsity constraints into auto-encoders and then propose a new auto-encoder algorithm called ...
Fingerprint. Dive into the research topics of 'HSAE: A Hessian regularized sparse auto-encoders'. Together they form a unique fingerprint.
Weifeng Liu, Tengzhou Ma, Dapeng Tao, Jane You : HSAE: A Hessian regularized sparse auto-encoders. Neurocomputing 187: 59-65 (2016).
Abstract— Recent researches have determined that regularized auto-encoders can provide a good representation of data which improves the performance of data ...
This work aims to review state-of-the-art auto-encoder algorithms. Firstly, we introduce the basic auto-encoder as well as its basic concept and structure.
