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|