Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Lossless model compression by batch normalization layer pruning in deep neural networks

Lossless model compression by batch normalization layer pruning in deep neural networks

US Patent 11488019 · Granted Nov 1, 2022

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Semiconductor device2025
Compute-In-Memory architecture using look-up tables2025
Catalyst including molecular sieve having topological pore structure, preparatio2025
Semiconductor device2024
Low precision and coarse-to-fine dynamic fixed-point quantization design in conv2024
Low precision and coarse-to-fine dynamic fixed-point quantization design in conv2024
Low precision and coarse-to-fine dynamic fixed-point quantization design in conv2024
Package structure with a barrier layer2024
Fast non-maximum suppression algorithm for object detection2023
Deep neural network with low-precision dynamic fixed-point in reconfigurable har2023
Deep neural network with low-precision dynamic fixed-point in reconfigurable har2023
Deep neural network with low-precision dynamic fixed-point in reconfigurable har2023