Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › System and method of encoding and decoding feature maps and weights for a convolutional neural network

System and method of encoding and decoding feature maps and weights for a convolutional neural network

US Patent 10726583 · Granted Jul 28, 2020

Estimated economic value: $26,273,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Dynamic cache allocation in artificial intelligence accelerator2025
Real time context dependent deep learning2025
Methods and apparatus to configure heterogenous components in an accelerator2025
Methods and apparatus to configure heterogenous components in an accelerator2025
Compression for deep learning in case of sparse values mapped to non-zero value2024
Compression for deep learning in case of sparse values mapped to non-zero value2024
Compression for deep learning in case of sparse values mapped to non-zero value2024
Inner product convolutional neural network accelerator2024
Secure distributed execution of jobs2024
Cloud policy enforcement based on network trust2024
Cloud-based tunnel protocol systems and methods for multiple ports and protocols2024
Systems and methods for troubleshooting and performance analysis of cloud-based 2024