System and method for pruning neural networks at initialization using iteratively conserving synaptic flow
US12406185B1 · kind B1 · utility
0Cited by
39References
16Claims
0Family size
Assignees
Inventors
Key dates
| Filing date | Jul 15, 2021 |
| Grant date | Sep 2, 2025 |
| Priority date | — |
| Expiry date | Jun 2, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/04
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system and method to prune parameters of a neural network at initialization uses iterative conserving synaptic flow that saves time, memory and energy both during training and at test time of the neural network. The result of the disclosed pruning system and method are highly sparse trainable subnetworks at initialization, without training and without ever looking at the data (a data agnostic pruning system and method). The pruning system and method preserves the total flow of synaptic strengths through the network at initialization subject to a sparsity constraint.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.