Barren plateaus in quantum neural network training landscapes
Gradient-based hybrid quantum-classical algorithms are often initialised with random, unstructured guesses. Here, the authors show that this approach will fail in the long run, due to the exponentially-small probability of finding a large enough gradient along any direction.
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2018
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/2d565792ea6b4691bd7767c8d897c439 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|