Machine-learning-based architecture search method for a neural network
US12175350B2 · kind B2 · utility
0Cited by
2References
25Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 10, 2019 |
| Grant date | Dec 24, 2024 |
| Priority date | — |
| Expiry date | Jun 26, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/047
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In at least one embodiment, differentiable neural architecture search and reinforcement learning are combined under one framework to discover network architectures with desired properties such as high accuracy, low latency, or both. In at least one embodiment, an objective function for search based on generalization error prevents the selection of architectures prone to overfitting.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.