Zhangyang Wang⁎; Ding Liu†; Thomas S. Huang‡ ⁎Department of Computer Science and Engineering, Texas A&M University, College Station, TX, United States†Beckman Institute for Advanced Science and Technology, Urbana, IL, United States‡Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Champaign, IL, United States
The first part of this chapter conducts an investigation of compressive sensing (CS) in the context of deep learning. We present a joint end-to-end optimization form of CS, and then propose a feed-forward pipeline to efficiently solve it as a deep neural network, called Deeply Optimized Compressive Sensing (DOCS). Rather than a data-driven “black ...
Get Deep Learning through Sparse and Low-Rank Modeling now with O’Reilly online learning.
O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.