Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Calibrating reliability of multi-label classification neural networks

Calibrating reliability of multi-label classification neural networks

US Patent 11507832 · Granted Nov 22, 2022

Estimated economic value: $3,534,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Representing sets of entities for matching problems2025
Automated hybrid pipeline for customer identification2024
Automated hybrid pipeline for customer identification2024
Graphical approach to multi-matching2023
Optimizing inference time of entity matching models2023
Identifying entities absent from training data using neural networks2022
Identifying entities absent from training data using neural networks2022
Vectorization of structured documents with multi-modal data2022
Generating explanations of machine learning predictions in matching problems2022
Learning system for contextual interpretation of Japanese words2022
Platform for preventing adversarial attacks on image-based machine learning mode2020