Quantizing autoencoders in a neural network
US11977388B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 21, 2019 |
| Grant date | May 7, 2024 |
| Priority date | — |
| Expiry date | Mar 25, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/088
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The performance of a neural network is improved by applying quantization to data at various points in the network. In an embodiment, a neural network includes two paths. A quantization is applied to each path, such that when an output from each path is combined, further quantization is not required. In an embodiment, the neural network is an autoencoder that includes at least one skip connection. In an embodiment, the system determines a set of quantization parameters based on the characteristics of the data in the primary path and in the skip connection, such that both network paths produce output data in the same fixed point format. As a result, the data from both network paths can be combined without requiring an additional quantization.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.