Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Layer-wise distillation for protecting pre-trained neural network models

Layer-wise distillation for protecting pre-trained neural network models

US Patent 11494637 · Granted Nov 8, 2022

Estimated economic value: $10,347,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Private computation of an agent data attribution score in collaborated task2025
Generating strong labels for examples labelled with weak labels2025
Recommendations based on private data using a dynamically deployed pre-filter2025
Using disentangled learning to train an interpretable deep learning model2025
Non-iterative federated learning2024
Recommendations based on private data using a dynamically deployed pre-filter2024
Anonymized time-series generation from recurrent neural networks2023
Distributed learning using ensemble-based fusion2023
Feature selection using Sobolev Independence Criterion2023
Network traffic rule identification2023
Determining value of corpora for machine learning using coresets2022
Recommendations based on private data using a dynamically deployed pre-filter2022