Amazon Technologies, Inc.

Asml Netherlands B.v.

Gang Chen

Long Gao

Eduardo Manuel Calleja

Te-Sheng Wang

William Shannon Fu

Techniques for high-performance machine learning (ML) inference in heterogenous edge devices are described. A ML model trained using a variety of different frameworks is translated into a common format that is runnable by inferences engines of edge devices. The translated model is optimized in hardware-agnostic and/or hardware-specific ways to improve inference performance, and the optimized model is sent to the edge devices. The inference engine for any edge device can be accessed by a customer application using a same defined API, regardless of the hardware characteristics of the edge device or the original format of the ML model.

High performance machine learning inference framework for edge devices

High perforamance machine learning inference framework for edge devices

Techniques for machine learning (ML) model knowledge distillation and automatic retraining are described. A model adaptation controller obtains samples generated by an edge device and inference values generated based on the samples by a deployed ML model of the edge device. The model adaptation controller runs inference on the samples using a different ML model to generate inferences that can be used to determine whether the performance of the deployed ML model is lacking. If so, the model adaptation controller can retrain the deployed ML model using samples with ground truth values generated by the different ML model, resulting in a light-weight retrained model that can be provisioned to the edge device. This retraining process may be performed iteratively to automatically improve and adapt the ML model running at the edge device.

Knowledge distillation and automatic model retraining via edge device sample collection

A method for improving a lithographic process for imaging a portion of a design layout onto a substrate using a lithographic apparatus, the method including: obtaining a relationship of a characteristic of one or more features in the portion with respect to dose; obtaining a value of the characteristic; and obtaining a target dose based on the value of the characteristic and the relationship.

Growing community of inventors

Fremont, CA, United States of America

Gang Chen