arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.04054stat.MLcs.LGcs.NE
收藏

一种用于深度卷积学习的生成模型

A Generative Model for Deep Convolutional Learning

Duke University(杜克大学)

Yunchen Pu, Xin Yuan, Lawrence Carin

摘要:

为深度(多层)卷积字典学习开发了一个生成模型。一种新的概率池化操作被集成到深度模型中,产生了高效的自底向上(预训练)和自顶向下(细化)的概率学习。实验结果表明,该模型具有强大的能力,从图像中学习多层特征,并在MNIST和Caltech 101数据集上获得了良好的分类结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑