Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic

Gowdra, N; Sinha, Roopak; MacDonell, S; Yan, WQ

Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic

journal contribution

posted on 2024-06-03, 02:59 authored by N Gowdra, Roopak SinhaRoopak Sinha, S MacDonell, WQ Yan

Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic

History

Journal

Pattern Recognition

Volume

119

Article number

108057

Pagination

1-12

Location

Amsterdam, The Netherlands

ISSN

0031-3203

eISSN

1873-5142

Language

eng

Publication classification

C1.1 Refereed article in a scholarly journal

Publisher

Elsevier

Publication URL

http://dx.doi.org/10.1016/j.patcog.2021.108057

Usage metrics

Keywords

Uncategorised value

Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic

History

Journal

Volume

Article number

Pagination

Location

ISSN

eISSN

Language

Publication classification

Publisher

Publication URL

Usage metrics

Categories

Keywords

Licence

Exports