On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks

Parsimonious representations are ubiquitous in modeling and processing information. Motivated by the recent Multi-Layer Convolutional Sparse Coding (ML-CSC) model, we herein generalize the traditional Basis Pursuit problem to a multi-layer setting, introducing similar sparse enforcing penalties at d...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 42; číslo 8; s. 1968 - 1980
Hlavní autoři:	Sulam, Jeremias, Aberdam, Aviad, Beck, Amir, Elad, Michael
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.08.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Analytical models Artificial neural networks Convolution Convolutional codes Dictionaries First order algorithms Fixed points (mathematics) Iterative algorithms Iterative methods iterative shrinkage algorithms Mathematical model Mathematical models Multi-layer convolutional sparse coding Multilayers network unfolding Neural networks Parameters recurrent neural networks Representations
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!