Výsledky vyhledávání

Akademický článek

On Learning and Learned Data Representation by Capsule Networks

Publikováno v: IEEE Access, Vol 7, Pp 50808-50822 (2019)

Capsule networks (CapsNet) are recently proposed neural network models containing newly introduced processing layer, which are specialized in entity representation and discovery in images. CapsNet is motivated by a view of parse tree-like information

Externí odkaz: https://doaj.org/article/8abc4c2b534d415cb9754a843d74b7b6

Zobrazit plný text záznamu

On Learning and Learned Data Representation by Capsule Networks

Autor: Zhenyuan Ma, Ancheng Lin, Jun Li

Publikováno v: IEEE Access, Vol 7, Pp 50808-50822 (2019)

© 2013 IEEE. Capsule networks (CapsNet) are recently proposed neural network models containing newly introduced processing layer, which are specialized in entity representation and discovery in images. CapsNet is motivated by a view of parse tree-li

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e16ee78b9eb1c684afa8a22baf8d0d4
https://hdl.handle.net/10453/139475

Zobrazit plný text záznamu

Multiple-task learning and knowledge transfer using generative adversarial capsule nets

Autor: Weiqi Luo, Zhenyuan Ma, Ancheng Lin, Jun Li, Lujuan Zhang

Publikováno v: AI 2018: Advances in Artificial Intelligence ISBN: 9783030039905
Australasian Conference on Artificial Intelligence

© Springer Nature Switzerland AG 2018. It is common that practical data has multiple attributes of interest. For example, a picture can be characterized in terms of its content, e.g. the categories of the objects in the picture, and in the meanwhile

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b669001b3249b21b5416812c315306d
https://hdl.handle.net/10453/134204

Zobrazit plný text záznamu

A New Family of Generative Adversarial Nets Using Heterogeneous Noise to Model Complex Distributions

Autor: Jun Li, Zhenyuan Ma, Lujuan Zhang, Lei Shi, Ancheng Lin

Publikováno v: AI 2018: Advances in Artificial Intelligence ISBN: 9783030039905
Australasian Conference on Artificial Intelligence

© Springer Nature Switzerland AG 2018. Generative adversarial nets (GANs) are effective framework for constructing data models and enjoys desirable theoretical justification. On the other hand, realizing GANs for practical complex data distribution

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6d05185e2e1faa89ef8d141bcf357656
https://doi.org/10.1007/978-3-030-03991-2_63

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání