Why do Deep Neural Networks with Skip Connections and Concatenated Hidden Representations Work?

Poster (Scientific congresses, symposiums and conference proceedings)

Oyedotun, Oyebade; Aouada, Djamila

2020 • The 27th International Conference on Neural Information Processing (ICONIP2020)

Permalink
https://hdl.handle.net/10993/44452

OyedotunAouada_ICONIP2020_full paper.pdf

Author postprint (2.13 MB)

All documents in ORBilu are protected by a user license.

Research center :

Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM

Disciplines :

Computer science

Author, co-author :

Oyedotun, Oyebade ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

Aouada, Djamila ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

External co-authors :

Language :

English

Title :

Why do Deep Neural Networks with Skip Connections and Concatenated Hidden Representations Work?

Publication date :

18 November 2020

Event name :

The 27th International Conference on Neural Information Processing (ICONIP2020)

Event date :

18-11-2020 to 22-11-2020

FnR Project :

FNR11295431 - Automatic Feature Selection For Visual Recognition, 2016 (01/02/2017-31/01/2021) - Oyebade Oyedotun

Funders :

FNR - Fonds National de la Recherche [LU]

Available on ORBilu :

since 15 October 2020

Number of views

126 (18 by Unilu)

Number of downloads

336 (14 by Unilu)