Learning Sparse Feature Representations Using Probabilistic Quadtrees and Deep Belief Nets

被引：53

作者：

Basu, Saikat ^{[1
]}

Karki, Manohar ^{[1
]}

Ganguly, Sangram ^{[2
]}

DiBiano, Robert ^{[5
]}

Mukhopadhyay, Supratik ^{[1
]}

Gayaka, Shreekant ^{[3
]}

Kannan, Rajgopal ^{[1
]}

Nemani, Ramakrishna ^{[4
]}

机构：

[1] Louisiana State Univ, Dept Comp Sci, Baton Rouge, LA 70803 USA

[2] NASA, BAERI, Ames Res Ctr, Moffett Field, CA 94035 USA

[3] Appl Mat Inc, Santa Clara, CA 95054 USA

[4] NASA, Adv Supercomp Div, Ames Res Ctr, Moffett Field, CA 94035 USA

[5] Autopredict Coding LLC, Baton Rouge, LA USA

来源：

NEURAL PROCESSING LETTERS | 2017年 / 45卷 / 03期

关键词：

Deep neural networks; Handwritten digit classification; Probabilistic quadtrees; Deep belief networks; Sparse feature representation;

D O I：

10.1007/s11063-016-9556-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：855 / 867

页数：13

共 18 条

[11] A fast learning algorithm for deep belief nets [J].

Hinton, Geoffrey E. ;

Osindero, Simon ;

Teh, Yee-Whye .

NEURAL COMPUTATION, 2006, 18 (07) :1527-1554

[12]

Koller D, 2009, Probabilistic graphical models: principles and techniques

[13]

Lazebnik S., COMPUTER VISION PATT, V2, P2169

[14]

Lee H., 2006, Adv Neural Inform Process Syst, V19, DOI DOI 10.5555/2976456.2976557

[15]

Miguel A, 2005, CONTRASTIVE DIVERGEN

[16] Acoustic Modeling Using Deep Belief Networks [J].

Mohamed, Abdel-rahman ;

Dahl, George E. ;

Hinton, Geoffrey .

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2012, 20 (01) :14-22

[17]

Ranzato M, 2008, ADV NEURAL INFORM PR

[18]

Srivastava N, 2014, J MACH LEARN RES, V15, P1929

← 1 2 →