Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Training neural networks based on dual pipeline architectures

Training neural networks based on dual pipeline architectures

US Patent 12511516 · Granted Dec 30, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Fairness and congestion control convergence2025
Neural network activation compression with narrow block floating-point2025
Deep learning scheduler toolkit2025
Weighted random early back-to-sender notification2025
Adaptive packet routing2025
Neural network activation compression with non-uniform mantissas2025
Recycled entropies packet spraying2025
Adjusting activation compression for neural network training2024
Neural network activation compression with non-uniform mantissas2024
Highly performant pipeline parallel deep neural network training2024
Neural network activation compression with outlier block floating-point2024
Method and apparatus for compressing and decompressing sparse data sets2024