Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Quantifying the predictive uncertainty of neural networks via residual estimation with I/O kernel

Quantifying the predictive uncertainty of neural networks via residual estimation with I/O kernel

US Patent 11681901 · Granted Jun 20, 2023

Estimated economic value: $168,493,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Digital key pairing method, pairing system, and vehicle2025
AI based optimized decision making for epidemiological modeling2025
System and method for evolved data augmentation and selection2025
Anti-cloning architecture for device identity provisioning2025
Anti-cloning of device cryptographic keys for counterfeit prevention2025
Transmission of secure information in a content distribution network2025
Loss function optimization using Taylor series expansion2025
Multiobjective coevolution of deep neural network architectures2025
Multiobjective coevolution of deep neural network architectures2025
Frame of folding tent2025
Frame of folding tent2025
Double-spliced foldable tent with central lifting and automatic opening and clos2025