Effect of Mutual Information on Chaotic Attractor Classification Accuracy Using Neural Network
Chaotic attractors can be classified by neural networks. However, its accuracy is incomplete. Because it varies greatly depending on the shape of the attractor. Also, the shape varies depending on mutual information. We investigated how the amount of mutual information in embedding affects the accuracy of attractor classification by neural networks.
Authors
- Yoshifumi Nishio (ORCID: https://orcid.org/0000-0002-0247-0001)
- Yoko Uwate (ORCID: https://orcid.org/0000-0002-2992-8852)
- Masaki Fujita (ORCID: https://orcid.org/0009-0009-9291-2464)
Institutions
- Tokushima University (JP)
Publication Details
- Published
- 2024-08-19
- DOI
- https://doi.org/10.1109/isocc62682.2024.10762586
- Primary Topic
- Neural Networks and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00