Fast deep neural network training
US10262240B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 14, 2017 |
| Grant date | Apr 16, 2019 |
| Priority date | — |
| Expiry date | Oct 3, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/764
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and computer programs are presented for training a deep neural network (DNN). One method includes an operation for training a predecessor network defined for image recognition of items, where parameters of a predecessor classifier are initialized with random numbers sampled from a predetermined distribution, and the predecessor classifier utilizes an image-classification probability function without bias. The method further includes an operation for training a successor network defined for image recognition of items in a plurality of classes, where parameters of a successor classifier are initialized with parameters learned from the predecessor network, and the successor classifier utilizes the image-classification probability function without bias. Further, the method includes operations for receiving an image for recognition, and recognizing the image utilizing the successor classifier.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.