Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets
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 quad trees and Deep Belief Nets. On the MNIST and n-MNIST data sets, our framework shows promising results and significantly outperforms traditional Deep Belief Networks.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 24, 2015
- Accession Number
- AD1010904
Entities
People
- Manohar Karki
- Ramakrishna Nemani
- Robert Di Biano
- Saikat Basu
- Sangram Ganguly
- Supratik Mukhopadhyay
Organizations
- Louisiana State University