Estimated online hard negative mining via probabilistic selection and scores history consideration
US12282848B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 17, 2020 |
| Grant date | Apr 22, 2025 |
| Priority date | — |
| Expiry date | Feb 9, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/09
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
According to one embodiment, a method, computer system, and computer program product for hard negative training is provided. The embodiment may include a computer receiving a training set, where the training set comprises one or more training samples. The computer trains a deep neural network (DNN) with the training set. The embodiment may also include determining, using the DNN, information for each of the one or more training samples, where the information includes one or more scores associated with the one or more training samples. The embodiment may further include generating a training epoch from the one or more training samples based on the information and updates the information based on using the training epoch with the DNN.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.