.png){kind=icon}
返回
Learning Deep Generative Models
.png){kind=icon}
OA
AI
DOI：10.1146/annurev-statistics-010814-020120.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Building intelligent systems that are capable of extracting high-level representations from high-dimensional sensory data lies at the core of solving many artificial intelligence-related tasks, including object recognition, speech perception, and language understanding. Theoretical and biological arguments strongly suggest that building such systems requires models with deep architectures that involve many layers of nonlinear processing. In this article, we review several popular deep learning models, including deep belief networks and deep Boltzmann machines. We show that (a) these deep generative models, which contain many layers of latent variables and millions of parameters, can be learned efficiently, and (b) the learned high-level feature representations can be successfully applied in many application domains, including visual object recognition, information retrieval, classification, and regression tasks.
Keyword:
deep learning
deep belief networks
deep Boltzmann machines
graphical models
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.7
论文数:
211
被引数:
2.4K
机构
引用论文
.png){kind=icon}
分享收藏Improved Particle Size Control for the Dispersion Polymerization of Methyl methacrylate in Supercritical Carbon Dioxide超临界二氧化碳中甲基丙烯酸甲酯分散聚合的改进粒度控制OAAI
OAAI分享收藏分享收藏
查看更多内容