公开(公告)号：US11295165B1

公开(公告)日：2022-04-05

申请号：US16587400

申请日：2019-09-30

Applicant: Amazon Technologies, Inc.

Inventor： Vinayak Ashutosh Agarwal ,  Jason Lenox Copeland ,  Matthew James Wood ,  Long Gao ,  Ricardo Elizondo Costa ,  Jiajun Sun ,  Naga Krishna Teja Komma

IPC: G06N20/00 ,  G06K9/62 ,  G06K9/00

Abstract: Techniques for training a machine learning model based on captured images are described. A method described include filtering a first set of collected images using one or more machine learning models; labeling the first set of filtered, collected images using a data labeling service using a service of the provider network; training a machine learning model from a machine learning algorithm using the first set of filtered, collected images using a service of the provider network; and causing deployment of the trained machine learning model onto a device.

公开(公告)号：US11704577B1

公开(公告)日：2023-07-18

申请号：US17716945

申请日：2022-04-08

Applicant: Amazon Technologies, Inc.

Inventor： Gang Chen ,  Long Gao ,  Eduardo Manuel Calleja

IPC: G06N5/02 ,  G06N20/00 ,  G06F16/11

CPC classification number: G06N5/027 ,  G06F16/116 ,  G06N20/00

Abstract: 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.

公开(公告)号：US11768914B1

公开(公告)日：2023-09-26

申请号：US17711391

申请日：2022-04-01

Applicant: Amazon Technologies, Inc.

Inventor： Vinayak Ashutosh Agarwal ,  Jason Lenox Copeland ,  Matthew James Wood ,  Long Gao ,  Ricardo Elizondo Costa ,  Jiajun Sun ,  Naga Krishna Teja Komma

IPC: G06N20/00 ,  G06F18/214 ,  G06V10/94 ,  G06F18/21 ,  G06F18/2413

CPC classification number: G06F18/214 ,  G06F18/217 ,  G06F18/2413 ,  G06N20/00 ,  G06V10/95

Abstract: Techniques for training a machine learning model based on captured images are described. A method described include filtering a first set of collected images using one or more machine learning models; labeling the first set of filtered, collected images using a data labeling service using a service of the provider network; training a machine learning model from a machine learning algorithm using the first set of filtered, collected images using a service of the provider network; and causing deployment of the trained machine learning model onto a device.

公开(公告)号：US11301762B1

公开(公告)日：2022-04-12

申请号：US16179217

申请日：2018-11-02

Applicant: Amazon Technologies, Inc.

Inventor： Gang Chen ,  Long Gao ,  Eduardo Manuel Calleja

IPC: G06N5/02 ,  G06N20/00 ,  G06F16/11

Abstract: 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.

公开(公告)号：US10990850B1

公开(公告)日：2021-04-27

申请号：US16217400

申请日：2018-12-12

Applicant: Amazon Technologies, Inc.

Inventor： Gang Chen ,  William Shannon Fu ,  Long Gao

IPC: G06K9/62 ,  G06N20/00

Abstract: 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.