.png){kind=icon}
返回
Deep Dictionary Learning
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2016.2611583.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Two popular representation learning paradigms are dictionary learning and deep learning. While dictionary learning focuses on learning basis'' and features'' by matrix factorization, deep learning focuses on extracting features via learning weights'' or filter'' in a greedy layer by layer fashion. This paper focuses on combining the concepts of these two paradigms by proposing deep dictionary learning and show how deeper architectures can be built using the layers of dictionary learning. The proposed technique is compared with other deep learning approaches, such as stacked autoencoder, deep belief network, and convolutional neural network. Experiments on benchmark data sets show that the proposed technique achieves higher classification and clustering accuracies. On a real-world problem of electrical appliance classification, we show that deep dictionary learning excels where others do not yield at-par performance. We postulate that the proposed formulation can pave the path for a new class of deep learning tools.
Keyword:
Deep learning
dictionary learning
feature representation
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:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Live attenuated measles virus induces regression of human lymphoma xenografts in immunodeficient mice.png)
BloodOAAI
BloodIF0
OAAI分享收藏Authors’ response: Importance of defining loss of response before therapeutic drug monitoringGut
GutIF0
PREAI
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Copper ferrocyanide loaded track etched membrane: an effective cesium adsorbent负载亚铁氰化铜的径迹蚀刻膜: 一种有效的铯吸附剂
PREAI
分享收藏A micromachined efficient parametric array loudspeaker with a wide radiation frequency band具有宽辐射频带的微机械高效参量阵列扬声器
PREAI
分享收藏
查看更多内容