公开(公告)号：US20240012852A1

公开(公告)日：2024-01-11

申请号：US17859915

申请日：2022-07-07

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Satish Kumar Mopur ,  Krishnaprasad Lingadahalli Shastry

IPC: G06F16/55 ,  G06V10/762 ,  G06V10/778

CPC classification number: G06F16/55 ,  G06V10/762 ,  G06V10/7796

Abstract: Bias in Machine Learning (ML) is when an ML algorithm tends to incompletely learn relevant and important patterns from a dataset, or learns the patterns from data incorrectly. Such inaccuracy can cause the algorithm to miss important relationships between patterns and features in data, resulting in inaccurate algorithm predictions. Systems and methods for detecting potential ML bias in input image datasets are described herein. After a target image is received, a subset of images related to the target image is extracted. The target image and subset of images are analyzed under an imbalance assessment and data bias assessment to determine the presence of any potential data bias in a ML training pipeline. If any data bias is determined, one or more messages summarizing the assessments and including explanations to enable more accurate predictions in image assessments are sent to the user.

公开(公告)号：US20240220514A1

公开(公告)日：2024-07-04

申请号：US18607923

申请日：2024-03-18

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Satish Kumar Mopur ,  Sridhar Balachandriah ,  Gunalan Perumal Vijayan ,  Suresh Ladapuram Soundararajan ,  Krishna Prasad Lingadahalli Shastry

IPC: G06F16/28 ,  G06F18/214 ,  G06F18/2321 ,  G06F18/23213 ,  G06F18/2413 ,  G06F18/2433

CPC classification number: G06F16/285 ,  G06F18/214 ,  G06F18/2321 ,  G06F18/23213 ,  G06F18/24137 ,  G06F18/2433

Abstract: The present invention relates to a system and a method for updating data models. Input data received from a data source and/or prediction data obtained from a data model is reduced based on baseline reference data to obtain a plurality of representative points. The plurality of representative points are clustered to generate a plurality of clusters. An outlier cluster is detected from the plurality of clusters based on a maximum distance of the plurality of clusters from a highest density cluster and/or comparison of quantity and values of the plurality of representative points with predefined rules. Data drift is identified based on changes in densities of the plurality of clusters. The data model is updated using information corresponding to the outlier cluster and the data drift.

公开(公告)号：US11954129B2

公开(公告)日：2024-04-09

申请号：US17225805

申请日：2021-04-08

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Satish Kumar Mopur ,  Sridhar Balachandriah ,  Gunalan Perumal Vijayan ,  Suresh Ladapuram Soundarajan ,  Krishna Prasad Lingadahalli Shastry

IPC: G06F16/28 ,  G06F18/214 ,  G06F18/2321 ,  G06F18/23213 ,  G06F18/2413 ,  G06F18/2433

CPC classification number: G06F16/285 ,  G06F18/214 ,  G06F18/2321 ,  G06F18/23213 ,  G06F18/24137 ,  G06F18/2433

Abstract: The present invention relates to a system and a method for updating data models. Input data received from a data source and/or prediction data obtained from a data model is reduced based on baseline reference data to obtain a plurality of representative points. The plurality of representative points are clustered to generate a plurality of clusters. An outlier cluster is detected from the plurality of clusters based on a maximum distance of the plurality of clusters from a highest density cluster and/or comparison of quantity and values of the plurality of representative points with predefined rules. Data drift is identified based on changes in densities of the plurality of clusters. The data model is updated using information corresponding to the outlier cluster and the data drift.

公开(公告)号：US11481665B2

公开(公告)日：2022-10-25

申请号：US16186422

申请日：2018-11-09

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Satish Kumar Mopur ,  Gregory S. Battas ,  Gunalan Perumal Vijayan ,  Krishnaprasad Lingadahalli Shastry ,  Saikat Mukherjee ,  Ashutosh Agrawal ,  Sridhar Balachandriah

IPC: G06N20/00 ,  H04L67/12 ,  G06N5/04 ,  G06N3/08

Abstract: A system and method for accounting for the impact of concept drift in selecting machine learning training methods to address the identified impact. Pattern recognition is performed on performance metrics of a deployed production model in an Internet-of-Things (IoT) environment to determine the impact that concept drift (data drift) has had on prediction performance. This concurrent analysis is utilized to select one or more approaches for training machine learning models, thereby accounting for the temporal dynamics of concept drift (and its subsequent impact on prediction performance) in a faster and more efficient manner.

公开(公告)号：US12088476B2

公开(公告)日：2024-09-10

申请号：US17933934

申请日：2022-09-21

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Satish Kumar Mopur ,  Saikat Mukherjee ,  Gunalan Perumal Vijayan ,  Sridhar Balachandriah ,  Ashutosh Agrawal ,  KrishnaPrasad Lingadahalli Shastry ,  Gregory S. Battas

IPC: H04L41/16 ,  G06N20/00 ,  H04L41/0816 ,  H04L41/22 ,  H04L43/045 ,  H04L43/091 ,  H04L67/125

CPC classification number: H04L41/16 ,  G06N20/00 ,  H04L41/0816 ,  H04L41/22 ,  H04L43/045 ,  H04L43/091 ,  H04L67/125

Abstract: The disclosure relates to a framework for dynamic management of analytic functions such as data processors and machine learned (“ML”) models for an Internet of Things intelligent edge that addresses management of the lifecycle of the analytic functions from creation to execution, in production. The end user will be seamlessly able to check in an analytic function, version it, deploy it, evaluate model performance and deploy refined versions into the data flows at the edge or core dynamically for existing and new end points. The framework comprises a hypergraph-based model as a foundation, and may use a microservices architecture with the ML infrastructure and models deployed as containerized microservices.

公开(公告)号：US20230017701A1

公开(公告)日：2023-01-19

申请号：US17933934

申请日：2022-09-21

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Satish Kumar Mopur ,  Saikat Mukherjee ,  Gunalan Perumal Vijayan ,  Sridhar Balachandriah ,  Ashutosh Agrawal ,  KrishnaPrasad Lingadahalli Shastry ,  Gregory S. Battas

IPC: H04L41/16 ,  H04L43/045 ,  H04L43/091 ,  H04L67/125 ,  H04L41/22 ,  G06N20/00 ,  H04L41/0816

Abstract: The disclosure relates to a framework for dynamic management of analytic functions such as data processors and machine learned (“ML”) models for an Internet of Things intelligent edge that addresses management of the lifecycle of the analytic functions from creation to execution, in production. The end user will be seamlessly able to check in an analytic function, version it, deploy it, evaluate model performance and deploy refined versions into the data flows at the edge or core dynamically for existing and new end points. The framework comprises a hypergraph-based model as a foundation, and may use a microservices architecture with the ML infrastructure and models deployed as containerized microservices.

公开(公告)号：US11469969B2

公开(公告)日：2022-10-11

申请号：US16152394

申请日：2018-10-04

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Satish Kumar Mopur ,  Saikat Mukherjee ,  Gunalan Perumal Vijayan ,  Sridhar Balachandriah ,  Ashutosh Agrawal ,  Krishnaprasad Lingadahalli Shastry ,  Gregory S. Battas

IPC: G06F15/173 ,  H04L41/16 ,  H04L67/125 ,  H04L43/045 ,  H04L41/0816 ,  H04L41/22 ,  G06N20/00 ,  H04L43/091

Abstract: The disclosure relates to a framework for dynamic management of analytic functions such as data processors and machine learned (“ML”) models for an Internet of Things intelligent edge that addresses management of the lifecycle of the analytic functions from creation to execution, in production. The end user will be seamlessly able to check in an analytic function, version it, deploy it, evaluate model performance and deploy refined versions into the data flows at the edge or core dynamically for existing and new end points. The framework comprises a hypergraph-based model as a foundation, and may use a microservices architecture with the ML infrastructure and models deployed as containerized microservices.

公开(公告)号：US11361245B2

公开(公告)日：2022-06-14

申请号：US16100076

申请日：2018-08-09

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Satish Kumar Mopur ,  Saikat Mukherjee ,  Gunalan Perumal Vijayan ,  Sridhar Balachandriah ,  Ashutosh Agrawal ,  Krishnaprasad Lingadahalli Shastry ,  Gregory S. Battas

IPC: G06F15/16 ,  G06N20/00 ,  H04L67/12 ,  G06F9/54

Abstract: The disclosure relates to technology that implements flow control for machine learning on data such as Internet of Things (“IoT”) datasets. The system may route outputs of a data splitter function performed on the IoT datasets to a designated target model based on a user specification for routing the outputs. In this manner, the IoT datasets may be dynamically routed to target datasets without reprogramming machine-learning pipelines, which enable rapid training, testing and validation of ML models as well as an ability to concurrently train, validate, and execute ML models.

公开(公告)号：US20190028407A1

公开(公告)日：2019-01-24

申请号：US15654846

申请日：2017-07-20

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Gunalan Perumal Vijayan ,  Saikat Mukherjee ,  Satish Kumar Mopur ,  Sridhar Balachandriah

IPC: H04L12/911 ,  H04L12/24 ,  H04L12/26 ,  H04L29/08

Abstract: Example implementations relate to managing compliance of workloads to quality of service (QoS) parameters. An example includes collection of time-series network performance data from server systems and fabric interconnects related to traffic generated by workloads of the server systems. Rapid trends and long term trends for the workloads are calculated, using the collected network performance data as the input. Compliance of a high priority workload to an associated QoS parameter with the high priority workload is managed based on monitoring a rapid analytic trend for the high priority workload. Compliance of all of the workloads to respective QoS parameters is managed based on monitoring of long term analytic trends for the workloads.