Discovering genomes to use in machine learning techniques
US11062792B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 18, 2017 |
| Grant date | Jul 13, 2021 |
| Priority date | — |
| Expiry date | Mar 13, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG16Z99/00
- WIPO fieldMeasurement
- WIPO sectorInstruments
Abstract
A facility for identifying combinations of feature and machine learning algorithm parameters, where each combination can be combined with one or more machine learning algorithms to train a model, is disclosed. The facility evaluates each genome based on the ability of a model trained using that genome and a machine learning algorithm to produce accurate results when applied to a validation data set by, for example, generating a fitness or validation score for the trained model and the corresponding genome used to train the model. Genomes that produce fitness scores that exceed a fitness threshold are selected for mutation, mutated, and the process is repeated. These trained models can then be applied to new data to generate predictions for the underlying subject matter.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.