Contrastive neural network training in an active learning environment
US11501165B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 4, 2020 |
| Grant date | Nov 15, 2022 |
| Priority date | — |
| Expiry date | Mar 31, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments relate to a system, program product, and method for training a contrastive neural network (CNN) in an active learning environment. A neural network is pre-trained with labeled data of a historical (first) dataset. The CNN is trained for a new (second) dataset by applying the new dataset and contrasting the new dataset against the historical dataset to extract novel patterns. Weights of a knowledge operator from the pre-trained neural network are borrowed. Features novel to the new dataset are learned, including updating weights of the knowledge operator. The borrowed knowledge operator weights are combined with the updated knowledge operator weights. The CNN is leveraged to predict one or more labels for the new dataset as output data.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.