Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks

Alberti M, Botros A, Schuetz N, Ingold R, Liwicki M, Seuret M (2021)

Publication Type: Conference contribution

Publication year: 2021

Journal

Proceedings - International Conference on Pattern Recognition

Publisher: IEEE COMPUTER SOC

City/Town: LOS ALAMITOS

Pages Range: 8204-8211

Conference Proceedings Title: 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)

Event location: , ELECTR NETWORK

DOI: 10.1109/ICPR48806.2021.9412204

Authors with CRIS profile

Mathias Seuret Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

University of Fribourg / Universitè de Fribourg CH Switzerland (CH) Universität Bern CH Switzerland (CH) Luleå University of Technology SE Sweden (SE)

How to cite

APA:

Alberti, M., Botros, A., Schuetz, N., Ingold, R., Liwicki, M., & Seuret, M. (2021). Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks. In 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (pp. 8204-8211). , ELECTR NETWORK: LOS ALAMITOS: IEEE COMPUTER SOC.

MLA:

Alberti, Michele, et al. "Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks." Proceedings of the 25th International Conference on Pattern Recognition (ICPR), , ELECTR NETWORK LOS ALAMITOS: IEEE COMPUTER SOC, 2021. 8204-8211.

BibTeX: Download