Invention Publication
- Patent Title: METHOD AND SYSTEM FOR A TEMPERATURE-RESILIENT NEURAL NETWORK TRAINING MODEL
-
Application No.: US18463778Application Date: 2023-09-08
-
Publication No.: US20240095528A1Publication Date: 2024-03-21
- Inventor: Jae-sun Seo , Jian Meng , Li Yang , Deliang Fan
- Applicant: Jae-sun Seo , Jian Meng , Li Yang , Deliang Fan
- Applicant Address: US AZ Tempe
- Assignee: Arizona Board of Regents on behalf of Arizona State University
- Current Assignee: Arizona Board of Regents on behalf of Arizona State University
- Current Assignee Address: US AZ Scottsdale
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/0495

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.
Information query