Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets
Computer Vision and Pattern Recognition
2015-09-14 v1
Abstract
Learning sparse feature representations is a useful instrument for solving an unsupervised learning problem. In this paper, we present three labeled handwritten digit datasets, collectively called n-MNIST. Then, we propose a novel framework for the classification of handwritten digits that learns sparse representations using probabilistic quadtrees and Deep Belief Nets. On the MNIST and n-MNIST datasets, our framework shows promising results and significantly outperforms traditional Deep Belief Networks.
Cite
@article{arxiv.1509.03413,
title = {Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets},
author = {Saikat Basu and Manohar Karki and Sangram Ganguly and Robert DiBiano and Supratik Mukhopadhyay and Ramakrishna Nemani},
journal= {arXiv preprint arXiv:1509.03413},
year = {2015}
}
Comments
Published in the European Symposium on Artificial Neural Networks, ESANN 2015