Skip to Main content Skip to Navigation
Journal articles

Deep octonion networks

Abstract : Deep learning is a hot research topic in the field of machine learning methods and applications. Real-value neural networks (Real NNs), especially deep real networks (DRNs), have been widely used in many research fields. In recent years, the deep complex networks (DCNs) and the deep quaternion networks (DQNs) have attracted more and more attentions. The octonion algebra, which is an extension of complex algebra and quaternion algebra, can provide more efficient and compact expressions. This paper constructs a general framework of deep octonion networks (DONs) and provides the main building blocks of DONs such as octonion convolution, octonion batch normalization and octonion weight initialization; DONs are then used in image classification tasks for CIFAR-10 and CIFAR-100 data sets. Compared with the DRNs, the DCNs, and the DQNs, the proposed DONs have better convergence and higher classification accuracy. The success of DONs is also explained by multi-task learning.
Complete list of metadatas

Cited literature [86 references]  Display  Hide  Download

https://hal-univ-rennes1.archives-ouvertes.fr/hal-02865295
Contributor : Laurent Jonchère <>
Submitted on : Friday, June 12, 2020 - 12:30:51 PM
Last modification on : Wednesday, June 17, 2020 - 9:49:34 AM

File

Wu et al-2020-Deep Octonion Ne...
Files produced by the author(s)

Identifiers

Collections

Citation

J. Wu, L. Xu, F. Wu, Y. Kong, L. Senhadji, et al.. Deep octonion networks. Neurocomputing, Elsevier, 2020, ⟨10.1016/j.neucom.2020.02.053⟩. ⟨hal-02865295⟩

Share

Metrics

Record views

39

Files downloads

8