Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Systems and methods for reducing power consumption of convolution operations for artificial neural networks

Systems and methods for reducing power consumption of convolution operations for artificial neural networks

US Patent 11763131 · Granted Sep 19, 2023

Estimated economic value: $738,520,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Apparatuses and methods to accelerate matrix multiplication2025
Artificial neural network training using flexible floating point tensors2025
Device and method for flexibly summing matrix values2023
Systems and methods for reducing data movement during convolution operations in 2023
Three-dimensional convolution pipeline with memory organizer unit2023
High bandwidth memory system with dynamically programmable distribution scheme2023
Point to point connected processing elements with data joiner components2023
Mechanism to perform non-linear functions in a machine learning accelerator2023
Systems and methods for reducing power consumption of convolution operations of 2023
Grouped convolution using point-to-point connected channel convolution engines2023
High bandwidth memory system with distributed request broadcasting masters2022
Mapping convolution to a channel convolution engine2022