Sequential training method for heterogeneous convolutional neural network
US11200438B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 9, 2019 |
| Grant date | Dec 14, 2021 |
| Priority date | — |
| Expiry date | Jun 16, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/96
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method of training a heterogeneous convolutional neural network (HCNN) system includes identifying batch sizes for a first task and a second task, defining images for a first batch, a second batch, and a batch x for the first task, defining images for a first batch, a second batch, and a batch y for the second task, training the HCNN using the first batch for the first task, training the HCNN using the first batch for the second task, training the HCNN using the second batch for the first task, training the HCNN using the second batch for the second task. The sequential training continues for each of the batches and each of the tasks until the end of an epoch. When the epoch is complete, the images for each batch and each task are reshuffled.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.