{"@context": "https://schema.org", "@type": "BreadcrumbList", "itemListElement": [{"@type": "ListItem", "position": 1, "name": "Home", "item": "https://www.patentleaderboard.com/"}, {"@type": "ListItem", "position": 2, "name": "Gradient normalization systems and methods for adaptive loss balancing in deep multitask networks", "item": "https://www.patentleaderboard.com/patent/11537895"}]}

Home › Gradient normalization systems and methods for adaptive loss balancing in deep multitask networks

Gradient normalization systems and methods for adaptive loss balancing in deep multitask networks

US Patent 11537895 · Granted Dec 27, 2022

Assignee

Magic Leap

Inventors

Zhao Chen (13 patents)
Vijay Badrinarayanan (35 patents)
Andrew Rabinovich (61 patents)

View full patent text on Google Patents →