Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Training method for quantizing the weights and inputs of a neural network

Training method for quantizing the weights and inputs of a neural network

US Patent 12288163 · Granted Apr 29, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Systems and methods for enhancement of 3D object detection using point cloud sem2025
Methods and systems for compressing a trained neural network and for improving e2025
Methods and systems for semantic segmentation of a point cloud2025
Selective neural network pruning by masking filters using scaling factors2024
Low resource computational block for a trained neural network2024
End to end differentiable machine vision systems, methods, and media2024
Method and system for graph-based panoptic segmentation2023
Systems and methods for generating amplifier gain models using active learning2023
System and method for bi-directional translation using sum-product networks2023