Patent · US Active

Automated generation of machine learning models

US11556778B2 · kind B2 · utility

1Cited by
0References
22Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 7, 2018
Grant dateJan 17, 2023
Priority date
Expiry dateJan 15, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F3/04847
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.