Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Reduction of parameters in fully connected layers of neural networks by low rank factorizations

Reduction of parameters in fully connected layers of neural networks by low rank factorizations

US Patent 10896366 · Granted Jan 19, 2021

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Method and system for content aware monitoring of media channel output by a medi2025
Systems and methods for processing data streams2025
Method and system for content aware monitoring of media channel output by a medi2024
Methods, systems, and media for random semi-structured row-wise pruning in neura2023
Facilitating robotic control using a virtual reality interface2023
Allocation of distributed data structures2022
Systems, methods and devices for a multistage sequential data process2021
Systems, methods and devices for a multistage sequential data process2021
System and method for training a neural network2020
System and method for training a neural network2020
Safety restraint2020
Systems, methods and devices for data quantization2020