Patent · US Active

Neural networks having reduced number of parameters

US12271812B2 · kind B2 · utility

0Cited by
0References
10Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 18, 2019
Grant dateApr 8, 2025
Priority date
Expiry dateJun 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.