Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets

2015/09/11 by Saikat Basu, Basu, Saikat, Manohar Karki +9
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning and Data Classification #Text and Document Classification Technologies #cs.CV

paper · pdf · doi:10.48550/arxiv.1509.03413

Published in the European Symposium on Artificial Neural Networks, ESANN 2015

arxiv created 2015/09/11 · openalex publication_date 2015/09/11 · arxiv updated 2015/09/14 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28

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.

Related

• A Fast Learning Algorithm for Deep Belief Nets
• A contextual analysis of multi-layer perceptron models in classifying hand-written digits and letters: limited resources
• A Hybrid Multi-Well Hopfield-CNN with Feature Extraction and K-Means for MNIST Classification
• Local Approximations, Real Interpolation and Machine Learning
• Sparse arrays of signatures for online character recognition