Learning Sparse Feature Representations Using Probabilistic Quadtrees and Deep Belief Nets

Authors

Saikat Basu, LSU College of Engineering
Manohar Karki, LSU College of Engineering
Sangram Ganguly, Bay Area Environmental Research Institute
Robert DiBiano, Autopredictive Coding LLC
Supratik Mukhopadhyay, LSU College of Engineering
Shreekant Gayaka, Applied Materials Incorporated
Rajgopal Kannan, LSU College of Engineering
Ramakrishna Nemani, NASA Ames Research Center

Document Type

Article

Publication Date

6-1-2017

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 by adding noise to the MNIST dataset, and three labeled datasets formed by adding noise to the offline Bangla numeral database. 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, n-MNIST and noisy Bangla datasets, our framework shows promising results and outperforms traditional Deep Belief Networks.

Publication Source (Journal or Book title)

Neural Processing Letters

First Page

855

Last Page

867

Recommended Citation

Basu, S., Karki, M., Ganguly, S., DiBiano, R., Mukhopadhyay, S., Gayaka, S., Kannan, R., & Nemani, R. (2017). Learning Sparse Feature Representations Using Probabilistic Quadtrees and Deep Belief Nets. Neural Processing Letters, 45 (3), 855-867. https://doi.org/10.1007/s11063-016-9556-4