Neuronal diversity can improve machine learning for physics and beyond
Abstract Diversity conveys advantages in nature, yet homogeneous neurons typically comprise the layers of artificial neural networks. Here we construct neural networks from neurons that learn their own activation functions, quickly diversify, and subsequently outperform their homogeneous counterpart...
| Päätekijät: | , , , , |
|---|---|
| Aineistotyyppi: | Artikkeli |
| Kieli: | English |
| Julkaistu: |
Nature Portfolio
2023-08-01
|
| Sarja: | Scientific Reports |
| Linkit: | https://doi.org/10.1038/s41598-023-40766-6 |