A generative model for deep convolutional learning

Yunchen Pu; Xin Yuan; Lawrence Carin

A generative model for deep convolutional learning

Yunchen Pu, Xin Yuan, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up (pretraining) and top-down (refinement) probabilistic learning. Experimental results demonstrate powerful capabilities of the model to learn multi-layer features from images, and excellent classification results are obtained on the MNIST and Caltech 101 datasets.

Original language	English (US)
Title of host publication	3rd International Conference on Learning Representations, ICLR 2015 - Workshop Track Proceedings
Publisher	International Conference on Learning Representations, ICLR
State	Published - Jan 1 2015
Externally published	Yes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2021-02-09

Cite this

@inproceedings{223873634d584657bcdc3b79ecf45fb0,

title = "A generative model for deep convolutional learning",

abstract = "A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up (pretraining) and top-down (refinement) probabilistic learning. Experimental results demonstrate powerful capabilities of the model to learn multi-layer features from images, and excellent classification results are obtained on the MNIST and Caltech 101 datasets.",

author = "Yunchen Pu and Xin Yuan and Lawrence Carin",

note = "Generated from Scopus record by KAUST IRTS on 2021-02-09",

year = "2015",

month = jan,

day = "1",

language = "English (US)",

booktitle = "3rd International Conference on Learning Representations, ICLR 2015 - Workshop Track Proceedings",

publisher = "International Conference on Learning Representations, ICLR",

}

TY - GEN

T1 - A generative model for deep convolutional learning

AU - Pu, Yunchen

AU - Yuan, Xin

AU - Carin, Lawrence

N1 - Generated from Scopus record by KAUST IRTS on 2021-02-09

PY - 2015/1/1

Y1 - 2015/1/1

N2 - A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up (pretraining) and top-down (refinement) probabilistic learning. Experimental results demonstrate powerful capabilities of the model to learn multi-layer features from images, and excellent classification results are obtained on the MNIST and Caltech 101 datasets.

AB - A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up (pretraining) and top-down (refinement) probabilistic learning. Experimental results demonstrate powerful capabilities of the model to learn multi-layer features from images, and excellent classification results are obtained on the MNIST and Caltech 101 datasets.

UR - http://www.scopus.com/inward/record.url?scp=85083953057&partnerID=8YFLogxK

M3 - Conference contribution

BT - 3rd International Conference on Learning Representations, ICLR 2015 - Workshop Track Proceedings

PB - International Conference on Learning Representations, ICLR

ER -

A generative model for deep convolutional learning

Abstract

Bibliographical note

Other files and links

Fingerprint

Cite this