Patent · US Active

Estimated online hard negative mining via probabilistic selection and scores history consideration

US12282848B2 · kind B2 · utility

0Cited by
4References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 17, 2020
Grant dateApr 22, 2025
Priority date
Expiry dateFeb 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.