Patent · US Active

Model matching and learning rate selection for fine tuning

US11164078B2 · kind B2 · utility

5Cited by
2References
15Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 8, 2017
Grant dateNov 2, 2021
Priority date
Expiry dateSep 3, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/0985
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method, computer system, and computer program product for model selection for training a new dataset is provided. The present invention may include choosing a model from a set of models to be evaluated for training the new dataset, selecting a sample input from a subset of the new dataset, calculating a model activation score for each of the sample inputs in the chosen model, calculating an accumulated model activation score for the chosen model, depending on the model activation score of each of the sample inputs in the chosen model, calculating an accumulated model activation score for each model from the set of models to be evaluated for training the new dataset, and selecting the model for training the new dataset with the highest accumulated model activation score.

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