Model matching and learning rate selection for fine tuning
US11164078B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 8, 2017 |
| Grant date | Nov 2, 2021 |
| Priority date | — |
| Expiry date | Sep 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.