公开(公告)号：US12293260B2

公开(公告)日：2025-05-06

申请号：US15884279

申请日：2018-01-30

Applicant: Amazon Technologies, Inc.

Inventor： Calvin Yue-Ren Kuo ,  Jiazhen Chen ,  Jingwei Sun ,  Haiyang Liu

IPC: G06N20/00 ,  G06F8/60 ,  G06F18/214 ,  G06N5/04 ,  H04W4/38

Abstract: A provider network implements a machine learning deployment service for generating and deploying packages to implement machine learning at connected devices. The service may receive from a client an indication of an inference application, a machine learning framework to be used by the inference application, a machine learning model to be used by the inference application, and an edge device to run the inference application. The service may then generate a package based on the inference application, the machine learning framework, the machine learning model, and a hardware platform of the edge device. To generate the package, the service may optimize the model based on the hardware platform of the edge device and/or the machine learning framework. The service may then deploy the package to the edge device. The edge device then installs the inference application and performs actions based on inference data generated by the machine learning model.

公开(公告)号：US11348029B1

公开(公告)日：2022-05-31

申请号：US15821515

申请日：2017-11-22

Applicant: Amazon Technologies, Inc.

Inventor： Jonathan I. Turow ,  Calvin Yue-Ren Kuo ,  Jiazhen Chen

IPC: G06N20/00

Abstract: Technology is described for providing machine learning (ML) models. A plurality of candidate ML models that are derived from a primary ML model may be generated in a service provider environment. The primary ML model may be associated with a set of parameters and a candidate ML model in the plurality of candidate ML models may be associated with a subset of the parameters associated with the primary ML model. The plurality of candidate ML models may be run against validation data to evaluate performance criteria for the candidate ML models. A performance representation of the candidate ML models with respect to performance results for the candidate ML models may be provided. An ML model may be selected from the performance representation based on the performance results for the candidate ML models.

公开(公告)号：US20190156246A1

公开(公告)日：2019-05-23

申请号：US15884279

申请日：2018-01-30

Applicant: Amazon Technologies, Inc.

Inventor： Calvin Yue-Ren Kuo ,  Jiazhen Chen ,  Jingwei Sun ,  Haiyang Liu

IPC: G06N99/00 ,  G06N5/04 ,  G06K9/62

Abstract: A provider network implements a machine learning deployment service for generating and deploying packages to implement machine learning at connected devices. The service may receive from a client an indication of an inference application, a machine learning framework to be used by the inference application, a machine learning model to be used by the inference application, and an edge device to run the inference application. The service may then generate a package based on the inference application, the machine learning framework, the machine learning model, and a hardware platform of the edge device. To generate the package, the service may optimize the model based on the hardware platform of the edge device and/or the machine learning framework. The service may then deploy the package to the edge device. The edge device then installs the inference application and performs actions based on inference data generated by the machine learning model.