公开(公告)号：US20190266015A1

公开(公告)日：2019-08-29

申请号：US15906963

申请日：2018-02-27

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ranveer Chandra ,  Rahul Anand Sharma

IPC: G06F9/48 ,  G06F9/50 ,  G06N3/08

Abstract: Systems, methods, and computer-executable instructions for scheduling neural network workloads on an edge device. A performance model for each neural network model is received. Parameters for each neural network workload is determined based on an associated performance model. Processing core assignments are determined from a plurality of processing cores for each neural network workload based on the corresponding performance model and processing core utilization. Image streams are received and associated with a neural network workload. Each neural network workload is scheduled to run on the processing cores based on the processing core assignments.

公开(公告)号：US10942767B2

公开(公告)日：2021-03-09

申请号：US15906963

申请日：2018-02-27

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ranveer Chandra ,  Rahul Anand Sharma

IPC: G06F9/48 ,  G06F9/50 ,  G06N3/00 ,  G06N3/08 ,  G06N3/04 ,  G06N3/063 ,  G06N3/02

Abstract: Systems, methods, and computer-executable instructions for scheduling neural network workloads on an edge device. A performance model for each neural network model is received. Parameters for each neural network workload is determined based on an associated performance model. Processing core assignments are determined from a plurality of processing cores for each neural network workload based on the corresponding performance model and processing core utilization. Image streams are received and associated with a neural network workload. Each neural network workload is scheduled to run on the processing cores based on the processing core assignments.

公开(公告)号：US11327476B2

公开(公告)日：2022-05-10

申请号：US16189736

申请日：2018-11-13

Applicant: Microsoft Technology Licensing, LLC

Inventor： Tusher Chakraborty ,  Akshay Uttama Nambi Srirangam Narashiman ,  Ranveer Chandra ,  Rahul Anand Sharma ,  Manohar Swaminathan ,  Zerina Kapetanovic ,  Jonathan Appavoo

IPC: G05B23/02 ,  G01D18/00 ,  G01N27/22

Abstract: A computer implemented method includes turning off a sensor, receiving fall curve data from the sensor, and comparing the received fall curve data to a set of fall curve signatures to identify the sensor or a sensor fault.

公开(公告)号：US20200150640A1

公开(公告)日：2020-05-14

申请号：US16189736

申请日：2018-11-13

Applicant: Microsoft Technology Licensing, LLC

Inventor： Tusher Chakraborty ,  Akshay Uttama Nambi Srirangam Narashiman ,  Ranveer Chandra ,  Rahul Anand Sharma ,  Manohar Swaminathan ,  Zerina Kapetanovic ,  Jonathan Appavoo

IPC: G05B23/02 ,  G01D18/00

Abstract: A computer implemented method includes turning off a sensor, receiving fall curve data from the sensor, and comparing the received fall curve data to a set of fall curve signatures to identify the sensor or a sensor fault.