Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Efficient processing of convolutional neural network layers using analog-memory-based hardware

Efficient processing of convolutional neural network layers using analog-memory-based hardware

US Patent 12111878 · Granted Oct 8, 2024

Estimated economic value: $24,159,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Two-dimensional mesh for compute-in-memory accelerator architecture2025
Efficient data layout and alignment for wide-vector accelerator systems2025
Buried metal signal rail for memory arrays2025
Split pulse width modulation to reduce crossbar array integration time2025
Memory cell in wafer backside2024
Array-integrated upstream/downstream router for circuit switched parallel connec2024
Row-by-row convolutional neural network mapping for analog artificial intelligen2024
Special-purpose digital-compute hardware for efficient element-wise aggregation,2024
System, method and article of manufacture for synchronization-free transmittal o2024
Synaptic weight transfer between conductance pairs with polarity inversion for r2024
Efficient tile mapping for row-by-row convolutional neural network mapping for a2024
Selective application of multiple pulse durations to crossbar arrays2023