Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Self-pruning neural networks for weight parameter reduction

Self-pruning neural networks for weight parameter reduction

US Patent 12505349 · Granted Dec 23, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Apparatus and method for generating efficient convolution2024
Piecewise quantization for neural networks2023
Normalization method for training deep neural networks2023
Lossless compression of neural network weights2023
Jointly pruning and quantizing deep neural networks2022
Jointly pruning and quantizing deep neural networks2022
Method for optimizing neural networks2022
Method to balance sparsity for efficient inference of deep neural networks2022
Self-pruning neural networks for weight parameter reduction2022
Self-pruning neural networks for weight parameter reduction2022
Accelerating long short-term memory networks via selective pruning2021
Accelerating long short-term memory networks via selective pruning2021