Invention Grant
- Patent Title: Automated problem detection for machine learning models
-
Application No.: US16588952Application Date: 2019-09-30
-
Publication No.: US11449798B2Publication Date: 2022-09-20
- 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
- Applicant: Amazon Technologies, Inc.
- Applicant Address: US WA Seattle
- Assignee: Amazon Technologies, Inc.
- Current Assignee: Amazon Technologies, Inc.
- Current Assignee Address: US WA Seattle
- Agency: Kowert, Hood, Munyon, Rankin & Goetzel, P.C.
- Agent Robert C. Kowert
- Main IPC: G06F11/00
- 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.
Public/Granted literature
- US20210097433A1 AUTOMATED PROBLEM DETECTION FOR MACHINE LEARNING MODELS Public/Granted day:2021-04-01
Information query