Patents

US 12755152 B2: Method and system for a temperature-resilient neural network training model

Granted
2026-10-06
Filed
2023-09-08 application 18463778
Type
Utility · 7 claims
Elsewhere
Google Patents ↗ · USPTO patent document ↗ · USPTO Patent Center record ↗

Abstract

A method for increasing the temperature-resiliency of a neural network, the method comprising loading a neural network model into a resistive nonvolatile in-memory-computing chip, training the deep neural network model using a progressive knowledge distillation algorithm as a function of a teacher model, the algorithm comprising injecting, using a clean model as the teacher model, low-temperature noise values into a student model and changing, now using the student model as the teacher model, the low-temperature noises to high-temperature noises, and training the deep neural network model using a batch normalization adaptation algorithm, wherein the batch normalization adaptation algorithm includes training a plurality of batch normalization parameters with respect to a plurality of thermal variations.

Source: PTBLXML, file of 2026-10-06 (ipgb20261006.xml).

Assignees

AssigneeTypePlaceAlso on furp.orgSource
Arizona Board of Regents on behalf of Arizona State University 1,571 patentsUS company or organizationScottsdale, AZPTBLXML, file of 2026-10-06

Inventors

InventorPlacePatentsPerson pageSource
Jae-sun SeoTempe, AZ33PTBLXML, file of 2026-10-06
Jian MengTempe, AZPTBLXML, file of 2026-10-06
Li YangTempe, AZPTBLXML, file of 2026-10-06
Deliang FanTempe, AZPTBLXML, file of 2026-10-06

CPC categories

SubclassCategoryFirst groupSource
G06NComputing arrangements based on specific computational modelsG06N3/08PTBLXML, file of 2026-10-06

Cooperative Patent Classification, as currently assigned (one row per subclass).

Assignments and security interests

No recorded assignments or security interests on file for this patent.

USPTO bulk data: PatentsView granted patents, disambiguated (PVGPATDIS) for patents, assignees, inventors, places and CPC categories; the USPTO Patent Assignment Dataset (ECORSEXC) for assignments and security interests. Patents filed in the last 20 years. No claims or full text. Links to other records are by name (and state): EXACT means the identical full name and state; FUZZY means a looser name match, with the confidence shown.