@inproceedings{e17b74cdb5e34775b7a55a49cc37b89f,
title = "Sparse hidden units activation in Restricted Boltzmann Machine",
abstract = "Sparsity has become a concept of interest in machine learning for many years. In deep learning sparse solutions play crucial role in obtaining robust and discriminative features. In this paper, we study a new regularization term for sparse hidden units activation in the context of Restricted Boltzmann Machine (RBM). Our proposition is based on the symmetric Kullback-Leibler divergence applied to compare the actual and the desired distribution over the active hidden units. We compare our method against two other enforcing sparsity regularization terms by evaluating the empirical classification error using two datasets: (i) for image classification (MNIST), (ii) for document classification (20-newsgroups).",
keywords = "Deep learning, sparse solution, symmetric Kullback-Leibler divergence",
author = "Tomczak, {Jakub M.} and Adam Gonczarek",
year = "2015",
month = jan,
day = "1",
doi = "10.1007/978-3-319-08422-0_27",
language = "English",
isbn = "9783319084213",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "181--185",
booktitle = "Progress in Systems Engineering - Proceedings of the 23rd International Conference on Systems Engineering",
address = "Germany",
note = "23rd International Conference on Systems Engineering, ICSEng 2014 ; Conference date: 19-08-2014 Through 21-08-2014",
}