公开(公告)号：US11449712B2

公开(公告)日：2022-09-20

申请号：US16220333

申请日：2018-12-14

Applicant: ADOBE INC.

Inventor： Deepak Pai ,  Vijay Srivastava ,  Joshua Sweetkind-Singer ,  Shankar Venkitachalam

IPC: G06K9/62 ,  G06F16/904 ,  G06N20/00 ,  G06N5/00

Abstract: In various embodiments of the present disclosure, output data generated by a deployed machine learning model may be received. An input data anomaly may be detected based at least in part on analyzing input data of the deployed machine learning model. An output data anomaly may further be detected based at least in part on analyzing the output data of the deployed machine learning model. A determination may be made that the input data anomaly contributed to the output data anomaly based at least in part on comparing the input data anomaly to the output data anomaly. A report may be generated that is indicative of the input data anomaly and the output data anomaly, and the report may be transmitted to a client device.

公开(公告)号：US20200234158A1

公开(公告)日：2020-07-23

申请号：US16253892

申请日：2019-01-22

Applicant: Adobe Inc.

Inventor： Deepak Pai ,  Joshua Sweetkind-Singer ,  Debraj Basu

IPC: G06N5/04 ,  G06N20/00

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for analyzing feature impact of a machine-learning model using prototypes across analytical spaces. For example, the disclosed system can identify features of data points used to generate outputs via a machine-learning model and then map the features to a feature space and the outputs to a label space. The disclosed system can then utilize an iterative process to determine prototypes from the data points based on distances between the data points in the feature space and the label space. Furthermore, the disclosed system can then use the prototypes to determine the impact of the features within the machine-learning model based on locally sensitive directions; region variability; or mean, range, and variance of features of the prototypes.

公开(公告)号：US11580420B2

公开(公告)日：2023-02-14

申请号：US16253892

申请日：2019-01-22

Applicant: Adobe Inc.

Inventor： Deepak Pai ,  Joshua Sweetkind-Singer ,  Debraj Basu

IPC: G06N5/04 ,  G06N20/00

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for analyzing feature impact of a machine-learning model using prototypes across analytical spaces. For example, the disclosed system can identify features of data points used to generate outputs via a machine-learning model and then map the features to a feature space and the outputs to a label space. The disclosed system can then utilize an iterative process to determine prototypes from the data points based on distances between the data points in the feature space and the label space. Furthermore, the disclosed system can then use the prototypes to determine the impact of the features within the machine-learning model based on locally sensitive directions; region variability; or mean, range, and variance of features of the prototypes.

公开(公告)号：US10699451B1

公开(公告)日：2020-06-30

申请号：US16224353

申请日：2018-12-18

Applicant: Adobe Inc.

Inventor： Deepak Pai ,  Kenneth Hahn ,  Joshua Sweetkind-Singer

IPC: G06T11/20 ,  G06K9/62 ,  G06F16/901

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for accurately, efficiently, and flexibly generating digital graphical representations reflecting multiple data series in-scale utilizing dynamic y-axes. In particular, in one or more embodiments, the disclosed systems generate a normalized graphical representation portraying multiple data series in a common scale with a dynamic y-axis that portrays individualized data values based on user selection of various data series. Specifically, the presently disclosed systems and methods can generate normalized values for each of the included data series, plot the normalized values along a normalized y-axis, and include a dynamic y-axis that reflects the initial values of any of the included data series.