System and method for emulating quantization noise for a neural network
US11972347B2 · kind B2 · utility
Assignees
Inventors
Key dates
| Filing date | Apr 22, 2019 |
| Grant date | Apr 30, 2024 |
| Priority date | — |
| Expiry date | Aug 30, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/09
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system for training a quantized neural network dataset, comprising at least one hardware processor adapted to: receive input data comprising a plurality of training input value sets and a plurality of target value sets; in each of a plurality of training iterations: for each layer, comprising a plurality of weight values, of one or more of a plurality of layers of a neural network: compute a set of transformed values by applying to a plurality of layer values one or more emulated non-uniformly quantized transformations by adding to each of the plurality of layer values one or more uniformly distributed random noise values; and compute a plurality of output values; compute a plurality of training output values; and update one or more of the plurality of weight values to decrease a value of a loss function; and output the updated plurality of weight values of the plurality of layers.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.