Neural networks having reduced number of parameters
US12271812B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 18, 2019 |
| Grant date | Apr 8, 2025 |
| Priority date | — |
| Expiry date | Jun 3, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/09
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes providing a neural network having a set of weights. The neural network receives an input data structure for generating a corresponding output array according to values of the set of weights. The neural network is trained to obtain a trained neural network. The training includes setting values of the set of weights with a gradient descent algorithm which exploits a cost function including a loss term and a regularization term. The trained neural network is deployed on a device through a communication network, and used by the device. The regularization term is based on a rate of change of elements of the output array caused by variations of the set of weights values.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.