Optimizer based prunner for neural networks
US12254412B2 · kind B2 · utility
0Cited by
3References
14Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 12, 2023 |
| Grant date | Mar 18, 2025 |
| Priority date | — |
| Expiry date | Jan 12, 2043 |
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.