Hyper parameter tuning for machine learning models

US12086725B2 · kind B2 · utility

Assignee

• Oracle International Corporation · US

Inventors

• Suresh Kumar Golconda · Seattle, US
• Vijayalakshmi Krishnamurthy · Sunnyvale, US
• Someshwar Maroti Kale · Kanchinakote, IN
• Sujay Sarkhel · San Jose, US
• Nickolas Kavantzas · Emerald Hills, US
• Mohan Kamath · Fremont, US
• Neelesh Kumar Shukla · Lucknow, IN
• Vidya Mani · Kanchinakote, IN
• Amit Vaid · Bengaluru, IN

Key dates

• Filing date: Aug 6, 2020
• Grant date: Sep 10, 2024
• Expiry date: Jun 12, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N20/00
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Techniques for selecting universal hyper parameters for use in a set of machine learning models across multiple computing environments include detection of a triggering condition for tuning a set of universal hyper parameters. The set of universal hyper parameters dictate configuration of the set of machine learning models that are independently executing, respectively, in the multiple computing environments. Based on the detected triggering condition, a first subset of universal hyper parameters from the set of universal hyper parameters are altered to generate a second set of universal hyper parameters. The second set of universal hyper parameters are applied to the set of machine learning models across the multiple computing environments.