公开(公告)号：US11610126B1

公开(公告)日：2023-03-21

申请号：US16447888

申请日：2019-06-20

Applicant: Amazon Technologies, Inc.

Inventor： David Heckerman ,  Mohammad Taha Bahadori ,  Zachary Chase Lipton

IPC: G06N3/00 ,  G06N3/084 ,  G06N20/10 ,  G06K9/62

Abstract: Techniques for generating multiple-resolutions of time series data are described. An input irregular time series having a plurality of data points is obtained, each data point of the plurality of data points including a timestamp and a feature vector. Based on the input irregular time series, multiple variant time series are generated. A data point in one of the variant time series is based in part on a combination of at least two data points of the input irregular time series. The multiple variant time series can then be used for machine learning tasks such as training a machine learning model or using a machine learning model to infer an output.