公开(公告)号：US11449798B2

公开(公告)日：2022-09-20

申请号：US16588952

申请日：2019-09-30

Applicant: Amazon Technologies, Inc.

Inventor： Andrea Olgiati ,  Maximiliano Maccanti ,  Arun Babu Nagarajan ,  Lakshmi Naarayanan Ramakrishnan ,  Urvashi Chowdhary ,  Gowda Dayananda Anjaneyapura Range ,  Zohar Karnin ,  Laurence Louis Eric Rouesnel ,  Stefano Stefani ,  Vladimir Zhukov

IPC: G06F11/00 ,  G06N20/00 ,  G06F11/07

Abstract: Methods, systems, and computer-readable media for automated problem detection for machine learning models are disclosed. A machine learning analysis system receives data associated with use of a machine learning model. The data was collected by a machine learning inference system and comprises input to the model or a plurality of inferences representing output of the machine learning model. The machine learning analysis system performs analysis of the data associated with the use of the machine learning model. The machine learning analysis system detects one or more problems associated with the use of the machine learning model based at least in part on the analysis. The machine learning analysis system initiates one or more remedial actions associated with the one or more problems associated with the use of the machine learning model.

公开(公告)号：US12118456B1

公开(公告)日：2024-10-15

申请号：US16198730

申请日：2018-11-21

Applicant: Amazon Technologies, Inc.

Inventor： Sahika Genc ,  Bharathan Balaji ,  Urvashi Chowdhary ,  Leo Parker Dirac ,  Saurabh Gupta ,  Vineet Khare ,  Sunil Mallya Kasaragod

IPC: G06N3/08 ,  G06F30/20

CPC classification number: G06N3/08 ,  G06F30/20

Abstract: A machine learning environment utilizing training data generated by customer networks. A reinforcement learning machine learning environment receives and processes training data generated by simulated hosted, or integrated, customer networks. The reinforcement learning machine learning environment corresponds to machine learning clusters that receive and process training data sets provided by the integrated customer networks. The customer networks include an agent process that collects training data and forwards the training data to the machine learning clusters. The machine learning clusters can be configured in a manner to automatically process the training data without requiring additional user inputs or controls to configure the application of the reinforcement learning machine learning processes.

公开(公告)号：US20210097433A1

公开(公告)日：2021-04-01

申请号：US16588952

申请日：2019-09-30

Applicant: Amazon Technologies, Inc.

Inventor： Andrea Olgiati ,  Maximiliano Maccanti ,  Arun Babu Nagarajan ,  Lakshmi Naarayanan Ramakrishnan ,  Urvashi Chowdhary ,  Gowda Dayananda Anjaneyapura Range ,  Zohar Karnin ,  Laurence Louis Eric Rouesnel ,  Stefano Stefani ,  Vladimir Zhukov

IPC: G06N20/00 ,  G06F11/07

Abstract: Methods, systems, and computer-readable media for automated problem detection for machine learning models are disclosed. A machine learning analysis system receives data associated with use of a machine learning model. The data was collected by a machine learning inference system and comprises input to the model or a plurality of inferences representing output of the machine learning model. The machine learning analysis system performs analysis of the data associated with the use of the machine learning model. The machine learning analysis system detects one or more problems associated with the use of the machine learning model based at least in part on the analysis. The machine learning analysis system initiates one or more remedial actions associated with the one or more problems associated with the use of the machine learning model.