English

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.

Keywords

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

R2 v1 2026-06-22T10:54:21.674Z