Small-world nets for fast neural network training and execution
US11625614B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 23, 2019 |
| Grant date | Apr 11, 2023 |
| Priority date | — |
| Expiry date | Nov 18, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/08
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method, a system, and a computer program product for fast training and/or execution of neural networks. A description of a neural network architecture is received. Based on the received description, a graph representation of the neural network architecture is generated. The graph representation includes one or more nodes connected by one or more connections. At least one connection is modified. Based on the generated graph representation, a new graph representation is generated using the modified at least one connection. The new graph representation has a small-world property. The new graph representation is transformed into a new neural network architecture.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.