Using quantization in training an artificial intelligence model in a semiconductor solution
US11475298B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 27, 2019 |
| Grant date | Oct 18, 2022 |
| Priority date | — |
| Expiry date | Apr 28, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system for training an artificial intelligence (AI) model for an AI chip to implement an AI task may include an AI training unit to train weights of an AI model in floating point, a convolution quantization unit for quantizing the trained weights to a number of quantization levels, and an activation quantization unit for updating the weights of the AI model so that output of the AI model based at least on the updated weights are within a range of activation layers of the AI chip. The updated weights may be stored in fixed point and uploadable to the AI chip. The various units may be configured to account for the hardware constraints in the AI chip to minimize performance degradation when the trained weights are uploaded to the AI chip and expedite training convergence. Forward propagation and backward propagation may be combined in training the AI model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.