Gradient adversarial training of neural networks
US12393847B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 10, 2024 |
| Grant date | Aug 19, 2025 |
| Priority date | — |
| Expiry date | May 10, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/082
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods for gradient adversarial training of a neural network are disclosed. In one aspect of gradient adversarial training, an auxiliary neural network can be trained to classify a gradient tensor that is evaluated during backpropagation in a main neural network that provides a desired task output. The main neural network can serve as an adversary to the auxiliary network in addition to a standard task-based training procedure. The auxiliary neural network can pass an adversarial gradient signal back to the main neural network, which can use this signal to regularize the weight tensors in the main neural network. Gradient adversarial training of the neural network can provide improved gradient tensors in the main network. Gradient adversarial techniques can be used to train multitask networks, knowledge distillation networks, and adversarial defense networks.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.