A generative model for deep convolutional learning
Publication
, Conference
Pu, Y; Yuan, X; Carin, L
Published in: 3rd International Conference on Learning Representations Iclr 2015 Workshop Track Proceedings
January 1, 2015
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.
Duke Scholars
Published In
3rd International Conference on Learning Representations Iclr 2015 Workshop Track Proceedings
Publication Date
January 1, 2015
Citation
APA
Chicago
ICMJE
MLA
NLM
Pu, Y., Yuan, X., & Carin, L. (2015). A generative model for deep convolutional learning. In 3rd International Conference on Learning Representations Iclr 2015 Workshop Track Proceedings.
Pu, Y., X. Yuan, and L. Carin. “A generative model for deep convolutional learning.” In 3rd International Conference on Learning Representations Iclr 2015 Workshop Track Proceedings, 2015.
Pu Y, Yuan X, Carin L. A generative model for deep convolutional learning. In: 3rd International Conference on Learning Representations Iclr 2015 Workshop Track Proceedings. 2015.
Pu, Y., et al. “A generative model for deep convolutional learning.” 3rd International Conference on Learning Representations Iclr 2015 Workshop Track Proceedings, 2015.
Pu Y, Yuan X, Carin L. A generative model for deep convolutional learning. 3rd International Conference on Learning Representations Iclr 2015 Workshop Track Proceedings. 2015.
Published In
3rd International Conference on Learning Representations Iclr 2015 Workshop Track Proceedings
Publication Date
January 1, 2015