Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets
This work addresses the problem of improving classification accuracy for handwritten digits, which is an incremental advancement in unsupervised learning for computer vision.
The paper tackles handwritten digit classification by proposing a novel framework that learns sparse feature representations using probabilistic quadtrees and Deep Belief Nets, achieving promising results and significantly outperforming traditional Deep Belief Networks on MNIST and n-MNIST datasets.
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.