生成式深度反卷积学习

Dec, 2014

Bayesian Deep Deconvolutional Learning

Yunchen Pu, Xin Yuan, Lawrence Carin

TL;DR基于生成贝叶斯模型，我们开发了深度卷积字典学习的新方法，并通过新概率汇聚运算提高了其效率，实验结果表明，这种方法在图像处理中能够很好地学习多层次特征，从而在MNIST和Caltech 101数据集上获得了非常好的分类结果。

Abstract

A generative bayesian model is developed for deep (multi-layer) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up and top-d