Neural network training with homomorphic encryption
US12130889B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 21, 2022 |
| Grant date | Oct 29, 2024 |
| Priority date | — |
| Expiry date | Jun 29, 2043 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L9/008
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method, a neural network, and a computer program product are provided that optimize training of neural networks using homomorphic encrypted elements and dropout algorithms for regularization. The method includes receiving, via an input to the neural network, a training dataset containing samples that are encrypted using homomorphic encryption. The method also includes determining a packing formation and selecting a dropout technique during training of the neural network based on the packing technique. The method further includes starting with a first packing formation from the training dataset, inputting the first packing formation in an iterative or recursive manner into the neural network using the selected dropout technique, with a next packing formation from the training dataset acting as an initial input that is applied to the neural network for a next iteration, until a stopping metric is produced by the neural network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.