Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Generating a compressed representation of a neural network with proficient inference speed and power consumption

Generating a compressed representation of a neural network with proficient inference speed and power consumption

US Patent 12346803 · Granted Jul 1, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Electrode structure for vertical group III-V device2025
Gallium nitride-based device with step-wise field plate and method making the sa2025
Spatial simulation method for assessment of direct economic losses of typhoon fl2025
Content-adaptive online training method and apparatus for deblocking in block-wi2025
Information sending method, information receiving method, terminal, and control 2025
Feedback information transmission method and apparatus, device, and medium2025
DNN-based cross component prediction2025
Systems for designing custom applications2025
Multi-task neural network by micro-structured parameter sharing for multi-qualit2025
Adaptive neural image compression with smooth quality control by meta-learning2025
Lightweight scalable multi-user optical antenna and communication method2025
Power control method and device2025