QQ客服 官方微博 反馈留言

	Multiscale Adaptive Representation of Signals: I. The Basic Framework
	Tai, Cheng ; E, Weinan
	2016
关键词	AdaFrame Dictionary Learning Wavelet Frames/Bi-frames LINEAR INVERSE PROBLEMS THRESHOLDING ALGORITHM SPARSE REPRESENTATION K-SVD DICTIONARIES IMAGES
英文摘要	We introduce a framework for designing multi-scale, adaptive, shift-invariant frames and bi-frames for representing signals. The new framework, called AdaFrame, improves over dictionary learning-based techniques in terms of computational efficiency at inference time. It improves classical multi-scale basis such as wavelet frames in terms of coding efficiency. It provides an attractive alternative to dictionary learning-based techniques for low level signal processing tasks, such as compression and denoising, as well as high level tasks, such as feature extraction for object recognition. Connections with deep convolutional networks are also discussed. In particular, the proposed framework reveals a drawback in the commonly used approach for visualizing the activations of the intermediate layers in convolutional networks, and suggests a natural alternative.; 973 program of the Ministry of Science and Technology of China; Major Program of NNSFC [91130005]; ONR grant [N00014-13-1-0338]; SCI(E); ARTICLE; CHENGT@MATH.PRINCETON.EDU; WEINAN@MATH.PRINCETON.EDU; 17
语种	英语
出处	SCI
出版者	JOURNAL OF MACHINE LEARNING RESEARCH
内容类型	其他
源URL	[http://hdl.handle.net/20.500.11897/459088]
专题	数学科学学院
推荐引用方式 GB/T 7714	Tai, Cheng,E, Weinan. Multiscale Adaptive Representation of Signals: I. The Basic Framework. 2016-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。