Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Methods and systems for compressing a trained neural network and for improving efficiently performing computations of a compressed neural network

Methods and systems for compressing a trained neural network and for improving efficiently performing computations of a compressed neural network

US Patent 12236337 · Granted Feb 25, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Training method for quantizing the weights and inputs of a neural network2025
Managed metastorage2025
Data sharing for network connected systems2024
Data sharing for network connected systems2024
Selective neural network pruning by masking filters using scaling factors2024
Low resource computational block for a trained neural network2024
Function creation for database execution of deep learning model2024
End to end differentiable machine vision systems, methods, and media2024
Methods and systems for product quantization-based compression of a matrix2024
Latent space and text-based generative adversarial networks (LATEXT-GANs) for te2023
Systems and methods for de novo peptide sequencing using deep learning and spect2023
Systems and methods for generating amplifier gain models using active learning2023