Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Decreasing neural network inference times using softmax approximation

Decreasing neural network inference times using softmax approximation

US Patent 10671909 · Granted Jun 2, 2020

Estimated economic value: $35,795,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Non-intrusive inspection methodology of landing base and surface pipe2025
Creating user interface using machine learning2025
Multiple fail-safe valves for safety of coiled tubing operations2025
Approximate k nearest neighbors on hardware accelerators2025
Neural networks based multimodal transformer for multi-task user interface model2025
Online detection device and method for underwater elements based on LIBS technol2025
Controlled adaptive optimization2025
Rotor assembly and compressor2025
Systems and methods for weighted quantization2025
Wake-up mechanism controlling method, electronic system, non-transitory computer2025
Smart metal-loss monitoring for coil tubing2025
Semiconductor light-emitting device2025