Optimizer based prunner for neural networks
US11580400B1 · kind B1 · utility
3Cited by
0References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 27, 2019 |
| Grant date | Feb 14, 2023 |
| Priority date | — |
| Expiry date | Aug 9, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A neural network pruning system can sparsely prune neural network models using an optimizer based approach that is agnostic to the model architecture being pruned. The neural network pruning system can prune by operating on the parameter vector of the full model and the gradient vector of the loss function with respect to the model parameters. The neural network pruning system can iteratively update parameters based on the gradients, while zeroing out as many parameters as possible based a preconfigured penalty.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.