Quaternion Convolutional Neural Networks: Current Advances and Future Directions
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914208401063936 |
|---|---|
| author | Altamirano-Gomez, Gerardo Gershenson, Carlos |
| author_facet | Altamirano-Gomez, Gerardo Gershenson, Carlos |
| contents | Since their first applications, Convolutional Neural Networks (CNNs) have solved problems that have advanced the state-of-the-art in several domains. CNNs represent information using real numbers. Despite encouraging results, theoretical analysis shows that representations such as hyper-complex numbers can achieve richer representational capacities than real numbers, and that Hamilton products can capture intrinsic interchannel relationships. Moreover, in the last few years, experimental research has shown that Quaternion-Valued CNNs (QCNNs) can achieve similar performance with fewer parameters than their real-valued counterparts. This paper condenses research in the development of QCNNs from its very beginnings. We propose a conceptual organization of current trends and analyze the main building blocks used in the design of QCNN models. Based on this conceptual organization, we propose future directions of research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_08663 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Quaternion Convolutional Neural Networks: Current Advances and Future Directions Altamirano-Gomez, Gerardo Gershenson, Carlos Artificial Intelligence Computer Vision and Pattern Recognition I.2.0; I.4.0; I.2.7 Since their first applications, Convolutional Neural Networks (CNNs) have solved problems that have advanced the state-of-the-art in several domains. CNNs represent information using real numbers. Despite encouraging results, theoretical analysis shows that representations such as hyper-complex numbers can achieve richer representational capacities than real numbers, and that Hamilton products can capture intrinsic interchannel relationships. Moreover, in the last few years, experimental research has shown that Quaternion-Valued CNNs (QCNNs) can achieve similar performance with fewer parameters than their real-valued counterparts. This paper condenses research in the development of QCNNs from its very beginnings. We propose a conceptual organization of current trends and analyze the main building blocks used in the design of QCNN models. Based on this conceptual organization, we propose future directions of research. |
| title | Quaternion Convolutional Neural Networks: Current Advances and Future Directions |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition I.2.0; I.4.0; I.2.7 |
| url | https://arxiv.org/abs/2307.08663 |