Restructuring deep neural networks to reduce the number of parameters
US11663443B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 21, 2018 |
| Grant date | May 30, 2023 |
| Priority date | — |
| Expiry date | Jun 12, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/082
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques are described for reducing the number of parameters of a deep neural network model. According to one or more embodiments, a device can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a structure extraction component that determines a number of input nodes associated with a fully connected layer of a deep neural network model. The computer executable components can further comprise a transformation component that replaces the fully connected layer with a number of sparsely connected sublayers, wherein the sparsely connected sublayers have fewer connections than the fully connecter layer, and wherein the number of sparsely connected sublayers is determined based on a defined decrease to the number of input nodes.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.