Reducing the size of a neural network through reduction of the weight matrices
US11030522B2 · kind B2 · utility
Inventors
Key dates
| Filing date | Oct 18, 2018 |
| Grant date | Jun 8, 2021 |
| Priority date | — |
| Expiry date | Dec 14, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/063
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods for reducing the size of neural networks are disclosed. In an embodiment, a server computer stores a plurality of training datasets, each of which comprise a plurality of training input matrices and a plurality of corresponding outputs. The server computer initiates training of a neural network using the plurality of training input matrices, a weight matrix, and the plurality of corresponding outputs. While the training of the neural network is being performed, the server computer identifies one or more weight values of the weight matrix for removal. The server computer removes the one or more weight values from the weight matrix to generate a reduced weight matrix. The server computer then stores the reduced weight matrix with the neural network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.