Tesla, inc. (20250005343). SYSTEM AND METHOD FOR ADAPTING A NEURAL NETWORK MODEL ON A HARDWARE PLATFORM

SYSTEM AND METHOD FOR ADAPTING A NEURAL NETWORK MODEL ON A HARDWARE PLATFORM

Organization Name

tesla, inc.

Inventor(s)

Michael Driscoll of Mountain View CA (US)

SYSTEM AND METHOD FOR ADAPTING A NEURAL NETWORK MODEL ON A HARDWARE PLATFORM

This abstract first appeared for US patent application 20250005343 titled 'SYSTEM AND METHOD FOR ADAPTING A NEURAL NETWORK MODEL ON A HARDWARE PLATFORM

Original Abstract Submitted

systems and methods for adapting a neural network model on a hardware platform. an example method includes obtaining neural network model information comprising decision points associated with a neural network, with one or more first decision points being associated with a layout of the neural network. platform information associated with a hardware platform for which the neural network model information is to be adapted is accessed. constraints associated with adapting the neural network model information to the hardware platform are determined based on the platform information, with a first constraint being associated with a processing resource of the hardware platform and with a second constraint being associated with a performance metric. a candidate configuration for the neural network is generated via execution of a satisfiability solver based on the constraints, with the candidate configuration assigns values to the plurality of decision points.