Class sparsity signature based Restricted Boltzmann Machine
详细信息 查看全文
- 作者：Anush Sankaran anushs@iiitd.ac.in" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Gaurav Goswami gauravgs@iiitd.ac.in" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Mayank Vatsa ; mayank@iiitd.ac.in" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Richa Singh rsingh@iiitd.ac.in" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Angshul Majumdar angshul@iiitd.ac.in" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Deep learning ; Sparsity ; Regularization ; Object recognition
- 刊名：Pattern Recognition
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：61
- 期：Complete
- 页码：674-685
- 全文大小：6946 K
文摘
- class="listitem" id="list_li0005">
- class="label">•
A supervised and semi-supervised approach to the RBM using class sparsity signature.
- class="label">•
Results of cssDBM and cssDBN along with dropout and dropconnect on MNIST, and CIFAR-10 databases.
- class="label">•
State-of-the-art results on one of the most challenging face database, Point and Shoot Challenge database.