Flow for quantized neural networks
US11645493B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 4, 2018 |
| Grant date | May 9, 2023 |
| Priority date | — |
| Expiry date | Jul 29, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/0985
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods and apparatus are disclosed supporting a design flow for developing quantized neural networks. In one example of the disclosed technology, a method includes quantizing a normal-precision floating-point neural network model into a quantized format. For example, the quantized format can be a block floating-point format, where two or more elements of tensors in the neural network share a common exponent. A set of test input is applied to a normal-precision flooding point model and the corresponding quantized model and the respective output tensors are compared. Based on this comparison, hyperparameters or other attributes of the neural networks can be adjusted. Further, quantization parameters determining the widths of data and selection of shared exponents for the block floating-point format can be selected. An adjusted, quantized neural network is retrained and programmed into a hardware accelerator.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.