18821724. OPTIMIZING NEURAL NETWORK STRUCTURES FOR EMBEDDED SYSTEMS (Tesla, Inc.)

OPTIMIZING NEURAL NETWORK STRUCTURES FOR EMBEDDED SYSTEMS

Organization Name

Tesla, Inc.

Inventor(s)

Harsimran Singh Sidhu of Fremont CA (US)

Paras Jagdish Jain of Cupertino CA (US)

Daniel Paden Tomasello of Los Altos Hills CA (US)

Forrest Nelson Iandola of San Jose CA (US)

OPTIMIZING NEURAL NETWORK STRUCTURES FOR EMBEDDED SYSTEMS

This abstract first appeared for US patent application 18821724 titled 'OPTIMIZING NEURAL NETWORK STRUCTURES FOR EMBEDDED SYSTEMS

Original Abstract Submitted

A model training and implementation pipeline trains models for individual embedded systems. The pipeline iterates through multiple models and estimates the performance of the models. During a model generation stage, the pipeline translates the description of the model together with the model parameters into an intermediate representation in a language that is compatible with a virtual machine. The intermediate representation is agnostic or independent to the configuration of the target platform. During a model performance estimation stage, the pipeline evaluates the performance of the models without training the models. Based on the analysis of the performance of the untrained models, a subset of models is selected. The selected models are then trained and the performance of the trained models are analyzed. Based on the analysis of the performance of the trained models, a single model is selected for deployment to the target platform.