Systems and methods for dividing filters in neural networks for private data computations
US11895220B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 16, 2021 |
| Grant date | Feb 6, 2024 |
| Priority date | — |
| Expiry date | Sep 6, 2041 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L2209/46
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes dividing a plurality of filters in a first layer of a neural network into a first set of filters and a second set of filters, applying each of the first set of filters to an input of the neural network, aggregating, at a second layer of the neural network, a respective one of a first set of outputs with a respective one of a second set of outputs, splitting respective weights of specific neurons activated in each remaining layer, at each specific neuron from each remaining layer, applying a respective filter associated with each specific neuron and a first corresponding weight, obtaining a second set of neuron outputs, for each specific neuron, aggregating one of the first set of neuron outputs with one of a second set of neuron outputs and generating an output of the neural network based on the aggregated neuron outputs.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.