公开(公告)号：US20230034011A1

公开(公告)日：2023-02-02

申请号：US17498124

申请日：2021-10-11

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Soumyendu Sarkar ,  Rohit Rawat ,  Vineet Gundecha ,  Sahand Ghorbanpour ,  Abhishek Jindal ,  Paolo Faraboschi

IPC: G06F16/33 ,  G06F40/216 ,  G06N20/00 ,  G06F16/338

Abstract: Examples described herein include a natural language processing (NLP) workflow for determining answers to queries. A query is received from a first client of a plurality of clients. A set of machine learning (ML) models are selected based on available service provider resources for processing the query. Each of the set of ML models corresponds to a respective stage of a NLP workflow. The query is input to a first model of the set of ML models. According to the NLP workflow, results from the first model are input to a second model of the set of ML models to determine a final result. A query answer based on the final result is transmitted to the first client.

公开(公告)号：US20210289171A1

公开(公告)日：2021-09-16

申请号：US16814454

申请日：2020-03-10

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Soumyendu Sarkar

IPC: H04N7/18 ,  G08B31/00 ,  G06K9/00

Abstract: Example implementations relate to tracking, by at least one image capture device, an object associated with an object of interest. An object of interest may be identified. The object of interest may be tracked, and one or more objects may be associated with the object of interest based on an interaction between the object of interest and the one or more associated objects. Subsequently, the object associated with the object of interest may be tracked.

公开(公告)号：US20240193927A1

公开(公告)日：2024-06-13

申请号：US18486756

申请日：2023-10-13

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Soumyendu Sarkar ,  Ashwin Ramesh Babu ,  Seyed Sajad Mousavi ,  Vineet Gundecha ,  Sahand Ghorbanpour ,  Avisek Naug

IPC: G06V10/82 ,  G06T5/00 ,  G06T7/11 ,  G06V10/776

CPC classification number: G06V10/82 ,  G06T5/001 ,  G06T7/11 ,  G06V10/776

Abstract: Systems and methods are provided for reinforcement Learning agents for adversarial black-box attacks to determine and refine robustness of a machine learning (ML) model. Examples include receiving an image corresponding to a ground truth and computing sensitivity of an ML model in classifying the image as the ground truth to added and removed distortions. An RL agent determines to add distortions to and remove distortions from the image based on the sensitivities. The ML Model classifies the image based on the added and removed distortions, and the process is repeated until the machine learning model misclassifies the image. Based on the misclassification, a measure of robustness is determined and/or the ML model can be retrained.