Machine learning model training using an analog processor

US12373687B2 · kind B2 · utility

Assignee

• Lightmatter, Inc. · US

Inventors

• Darius Bunandar · Boston, US
• Ludmila Levkova · Brooklyn, US
• Nicholas Dronen · Eindhoven, NL
• Lakshmi Nair · Somerville, US
• David Widemann · Danville, US
• David Walter · Cambridge, US
• Martin B. Z. Forsythe · Brookline, US
• Tomo Lazovich · Cambridge, US
• Ayon Basumallik · Framingham, US
• Nicholas C. Harris · Menlo Park, US

Key dates

• Filing date: Nov 29, 2021
• Grant date: Jul 29, 2025
• Expiry date: May 30, 2044

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N20/10
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Described herein are techniques of training a machine learning model and performing inference using an analog processor. Some embodiments mitigate the loss in performance of a machine learning model resulting from a lower precision of an analog processor by using an adaptive block floating-point representation of numbers for the analog processor. Some embodiments mitigate the loss in performance of a machine learning model due to noise that is present when using an analog processor. The techniques involve training the machine learning model such that it is robust to noise.