Edge calculation-oriented reparametric neural network architecture search method
US11645495B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 16, 2022 |
| Grant date | May 9, 2023 |
| Priority date | — |
| Expiry date | Aug 16, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/048
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present invention discloses an edge calculation-oriented reparametric neural network architecture search method, including the following steps: S1: designing linear operators and multi-branch block structures; S2: constructing a hypernetwork by stacking the multi-branch block structures; S3: training the hypernetwork through a gradient-based first-stage search algorithm; S4: deleting redundant branches in the hypernetwork to construct an optimal subnetwork; S5: converting the multi-branch optimal subnetwork into a single-branch network; and S6: completing task reasoning by using the single-branch network. The method is used to search the neural network structure capable of performing reparameterization, and ensures the reasoning real-time performance and the high efficiency of model operation while ensuring the reasoning precision.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.