Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Reconfigurable memory compression techniques for deep neural networks

Reconfigurable memory compression techniques for deep neural networks

US Patent 11625584 · Granted Apr 11, 2023

Estimated economic value: $27,486,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

End-to-end data protection for compute in memory (CIM)/compute near memory (CNM)2025
Multi-buffered register files with shared access circuits2025
Side-channel resistant multiplicatively masked encryption engine with zero-value2025
LSTM circuit with selective input computation2025
LSTM circuit with selective input computation2025
LSTM circuit with selective input computation2025
LSTM circuit with selective input computation2025
LSTM circuit with selective input computation2025
Multi-height interconnect trenches for resistance and capacitance optimization2025
Technologies for memory and I/O efficient operations on homomorphically encrypte2025
Apparatus and method for approximate trilinear interpolation for scene reconstru2025
Apparatus and method for approximate trilinear interpolation for scene reconstru2025