Cascaded Compressed Sensing Networks: A Reversible Architecture for Layerwise Learning

10/20/2021
by   Weizhi Lu, et al.
0

Recently, the method that learns networks layer by layer has attracted increasing interest for its ease of analysis. For the method, the main challenge lies in deriving an optimization target for each layer by inversely propagating the global target of the network. The propagation problem is ill posed, due to involving the inversion of nonlinear activations from lowdimensional to high-dimensional spaces. To address the problem, the existing solution is to learn an auxiliary network to specially propagate the target. However, the network lacks stability, and moreover, it results in higher complexity for network learning. In the letter, we show that target propagation could be achieved by modeling the network s each layer with compressed sensing, without the need of auxiliary networks. Experiments show that the proposed method could achieve better performance than the auxiliary network-based method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/05/2018

Randomness and isometries in echo state networks and compressed sensing

Although largely different concepts, echo state networks and compressed ...
research
10/13/2021

ADMM-DAD net: a deep unfolding network for analysis compressed sensing

In this paper, we propose a new deep unfolding neural network based on t...
research
06/23/2022

Global Sensing and Measurements Reuse for Image Compressed Sensing

Recently, deep network-based image compressed sensing methods achieved h...
research
04/13/2018

An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios

The compressed sensing (CS) has been successfully applied to image compr...
research
08/03/2022

Fast Hierarchical Deep Unfolding Network for Image Compressed Sensing

By integrating certain optimization solvers with deep neural network, de...
research
03/09/2023

Generalization analysis of an unfolding network for analysis-based Compressed Sensing

Unfolding networks have shown promising results in the Compressed Sensin...

Please sign up or login with your details

Forgot password? Click here to reset