Reducing the size of a neural network through reduction of the weight matrices
US10127495B1 · kind B1 · utility
Inventors
Key dates
| Filing date | Apr 14, 2017 |
| Grant date | Nov 13, 2018 |
| Priority date | — |
| Expiry date | Jun 11, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/063
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods for reducing the size of deep 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 deep neural network using the plurality of training input matrices, a weight matrix, and the plurality of corresponding outputs. While the training of the deep 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 deep neural network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.