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.
Cite
Text
Pu et al. "A Generative Model for Deep Convolutional Learning." International Conference on Learning Representations, 2015.Markdown
[Pu et al. "A Generative Model for Deep Convolutional Learning." International Conference on Learning Representations, 2015.](https://mlanthology.org/iclr/2015/pu2015iclr-generative/)BibTeX
@inproceedings{pu2015iclr-generative,
title = {{A Generative Model for Deep Convolutional Learning}},
author = {Pu, Yunchen and Yuan, Xin and Carin, Lawrence},
booktitle = {International Conference on Learning Representations},
year = {2015},
url = {https://mlanthology.org/iclr/2015/pu2015iclr-generative/}
}