Learning Sparse Feature Representations Using Probabilistic Quadtrees and Deep Belief Nets
By Saikat Basu, Manohar Karki, Sangram Ganguly, Robert DiBiano, Supratik Mukhopadhyay, Shreekant Gayaka, Rajgopal Kannan, R. Nemani. 2015
83 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Samuel F. Dodge
- Supratik Mukhopadhyay
- Saikat Basu
- Manohar Karki
- Hazim Kemal Ekenel
- Robert DiBiano
- Lina Karam
- R. Nemani
In Computer Vision and Pattern Recognition
- Samuel F. Dodge
- Lina Karam
- Supratik Mukhopadhyay
- Samil Karahan
- Saikat Basu
- Manohar Karki
- Hazim Kemal Ekenel
- Robert DiBiano
Citations in the corpus
- How Image Degradations Affect Deep CNN-Based Face Recognition? (2016, background): “Besides face recognition, image quality effects are also studied in different classification applications, such as object classification [8] and hand-written digit recognition [9].”
- Understanding how image quality affects deep neural networks (2016, methodology): “Additionally, the authors in [11] propose a modification of deep belief networks to achieve greater accuracy on this dataset.”
- DeepSat: a learning framework for satellite imagery (2015, methodology): “They have also been found useful in hybrid learning models for noisy handwritten digit classification [2].”