Pith. sign in

REVIEW 3 cited by

Compressed Learning: A Deep Neural Network Approach

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1610.09615 v1 pith:GXFMIEXS submitted 2016-10-30 cs.CV

Amir Adler , Michael Elad , Michael Zibulevsky This is my paper · ORCID
classification cs.CV
keywords learningapproachinferencesensingsignalclassificationcompresseddeep
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Compressed Learning (CL) is a joint signal processing and machine learning framework for inference from a signal, using a small number of measurements obtained by linear projections of the signal. In this paper we present an end-to-end deep learning approach for CL, in which a network composed of fully-connected layers followed by convolutional layers perform the linear sensing and non-linear inference stages. During the training phase, the sensing matrix and the non-linear inference operator are jointly optimized, and the proposed approach outperforms state-of-the-art for the task of image classification. For example, at a sensing rate of 1% (only 8 measurements of 28 X 28 pixels images), the classification error for the MNIST handwritten digits dataset is 6.46% compared to 41.06% with state-of-the-art.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Learning Sub-Sampling and Signal Recovery with Applications in Ultrasound Imaging

    eess.IV 2019-08 conditional novelty 7.0 of 10

    DPS jointly learns a probabilistic sub-sampling pattern and a neural reconstruction network, producing task-specific sparse sampling schemes for partial Fourier and ultrasound data.

  2. Optimized Sampling of Angle-Resolved Scatterometry Data Using End-to-End Compressed Learning Model for Nanograss Deficiency Detection

    eess.SP 2026-06 unverdicted novelty 6.0 of 10

    An end-to-end learnable latitude-based sampling layer with CNN matches full ARS image accuracy for 5-level nanograss deficiency classification using up to 99.7% fewer sampling points.

  3. Learning the Mathematical Property for Designing Low Mutual Coherence Binary Sensing Matrices

    cs.LG 2026-08 conditional novelty 5.0 of 10

    A neural network can generate binary sensing matrices with lower mutual coherence than random matrices by optimizing coherence-based losses without any training data.

Pith tools