Jump to content

20250190813. Fine-tuning Ne (Advanced Micro Devices, .)

From WikiPatents

FINE-TUNING OF NEURAL NETWORKS

Abstract: techniques are described for fine-tuning a neural network. a plurality of fine-tuning layers of a neural network are executed, each corresponding to a respective reference layer of a reference neural network. for each of the fine-tuning layers, a fine-tuning weight matrix is generated based on a reference weight matrix associated with the corresponding reference layer. one or more weights of the fine-tuning weight matrix are then iteratively adjusted based on a comparison of the output of the fine-tuning layer with the output of the corresponding reference layer.

Inventor(s): Adam H. Li, Alireza Khodamoradi, Benjamin T. Sander, Eric Ford Dellinger, Kristof Denolf, Philip B. James-Roxby, Ralph Wittig

CPC Classification: G06N3/098 (Distributed learning, e.g. federated learning)

Search for rejections for patent application number 20250190813


Cookies help us deliver our services. By using our services, you agree to our use of cookies.