Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Low-overhead error prediction and preemption in deep neural network using apriori network statistics

Low-overhead error prediction and preemption in deep neural network using apriori network statistics

US Patent 11016840 · Granted May 25, 2021

Estimated economic value: $5,474,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Using an ensemble of data transformers to encode data before zero-value compress2025
Managing power for serverless computing2025
Controlling speculative actions based on a hit/miss predictor2025
Detecting and mitigating false structure sharing within a cache line2025
Stickification using anywhere padding to accelerate data manipulation2025
Training convolution neural network on analog resistive processing unit system2025
Padding input data for artificial intelligence accelerators2025
Instruction execution scheduling using a hit/miss predictor2025
Location-aware protection system of latches (LAPS-L)2025
Location-aware protection system of latches (LAPS-L)2025
Location-aware protection system of latches (LAPS-L)2025
Single function to perform combined matrix multiplication and bias add operation2025