KHNN: Hypercomplex-valued neural networks computations via Keras using TensorFlow and PyTorch
Neural networks that utilize algebras more advanced than real numbers, such as hypercomplex numbers, can outperform traditional models in certain applications, usually, in the number of training parameters giving the same accuracy. However, no general framework exists for constructing hypercomplex n...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-05-01
|
| Series: | SoftwareX |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S235271102500130X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|