Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Heterogeneous architecture for depthwise-seperable convolution based neural network computation acceleration

Heterogeneous architecture for depthwise-seperable convolution based neural network computation acceleration

US Patent 12430544 · Granted Sep 30, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

High-performance on-chip memory controller2025
High-performance on-chip memory controller2025
Integer-based fused convolutional layer in a convolutional neural network2024
Targeted therapy composition and its use for suppressing breast cancer cell prol2024
High-performance on-chip memory controller2024
High-performance on-chip memory controller2024
Large touch display integrated system and driving signal processing method there2024
Extensible multi-precision data pipeline for computing non-linear and arithmetic2023
Extensible multi-precision data pipeline for computing non-linear and arithmetic2023
Heterogeneous computation and hierarchical memory image sensing pipeline2023
Unified flow control for multi-camera system2022
LiDAR assisted wheel encoder to camera calibration2022