公开(公告)号：US10902293B2

公开(公告)日：2021-01-26

申请号：US16177581

申请日：2018-11-01

Applicant: Cisco Technology, Inc.

Inventor： Purushotham Kamath ,  Abhishek Singh ,  Debojyoti Dutta

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: In one embodiment, a device forms a neural network envelope cell that comprises a plurality of convolution-based filters in series or parallel. The device constructs a convolutional neural network by stacking copies of the envelope cell in series. The device trains, using a training dataset of images, the convolutional neural network to perform image classification by iteratively collecting variance metrics for each filter in each envelope cell, pruning filters with low variance metrics from the convolutional neural network, and appending a new copy of the envelope cell into the convolutional neural network.

公开(公告)号：US20190286945A1

公开(公告)日：2019-09-19

申请号：US16177581

申请日：2018-11-01

Applicant: Cisco Technology, Inc.

Inventor： Purushotham Kamath ,  Abhishek Singh ,  Debojyoti Dutta

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: In one embodiment, a device forms a neural network envelope cell that comprises a plurality of convolution-based filters in series or parallel. The device constructs a convolutional neural network by stacking copies of the envelope cell in series. The device trains, using a training dataset of images, the convolutional neural network to perform image classification by iteratively collecting variance metrics for each filter in each envelope cell, pruning filters with low variance metrics from the convolutional neural network, and appending a new copy of the envelope cell into the convolutional neural network.

公开(公告)号：US20190303018A1

公开(公告)日：2019-10-03

申请号：US15943640

申请日：2018-04-02

Applicant: Cisco Technology, Inc.

Inventor： Xinyuan Huang ,  Johnu George ,  Marc Solanas Tarre ,  Komei Shimamura ,  Purushotham Kamath ,  Debojyoti Dutta

IPC: G06F3/06 ,  G06F9/48 ,  G06F17/30

Abstract: Aspects of the technology provide improvements to a Serverless Computing (SLC) workflow by determining when and how to optimize SLC jobs for computing in a Distributed Computing Framework (DCF). DCF optimization can be performed by abstracting SLC tasks into different workflow configurations to determined optimal arrangements for execution in a DCF environment. A process of the technology can include steps for receiving an SLC job including one or more SLC tasks, executing one or more of the tasks to determine a latency metric and a throughput metric for the SLC tasks, and determining if the SLC tasks should be converted to a Distributed Computing Framework (DCF) format based on the latency metric and the throughput metric. Systems and machine-readable media are also provided.

公开(公告)号：US20190149440A1

公开(公告)日：2019-05-16

申请号：US15810552

申请日：2017-11-13

Applicant: Cisco Technology, Inc.

Inventor： Ralf Rantzau ,  Xinyuan Huang ,  Purushotham Kamath ,  Debojyoti Dutta

IPC: H04L12/26 ,  H04L29/06

Abstract: In one embodiment, a service converts a stream of network telemetry data into sketches. The stream of network telemetry data comprises a plurality of characteristics of traffic observed in a network. The service forms a time series of the sketches. The service performs anomaly detection on the time series of the sketches in part by calculating a joint distribution of ranks and frequencies of a portion of the characteristics at different points in time of the time series. The service sends an anomaly detection alert, when an anomaly is detected from the time series of the sketches.

公开(公告)号：US10678444B2

公开(公告)日：2020-06-09

申请号：US15943640

申请日：2018-04-02

Applicant: Cisco Technology, Inc.

Inventor： Xinyuan Huang ,  Johnu George ,  Marc Solanas Tarre ,  Komei Shimamura ,  Purushotham Kamath ,  Debojyoti Dutta

IPC: G06F3/06 ,  G06F9/48 ,  G06F16/25

Abstract: Aspects of the technology provide improvements to a Serverless Computing (SLC) workflow by determining when and how to optimize SLC jobs for computing in a Distributed Computing Framework (DCF). DCF optimization can be performed by abstracting SLC tasks into different workflow configurations to determined optimal arrangements for execution in a DCF environment. A process of the technology can include steps for receiving an SLC job including one or more SLC tasks, executing one or more of the tasks to determine a latency metric and a throughput metric for the SLC tasks, and determining if the SLC tasks should be converted to a Distributed Computing Framework (DCF) format based on the latency metric and the throughput metric. Systems and machine-readable media are also provided.

公开(公告)号：US11016673B2

公开(公告)日：2021-05-25

申请号：US15931302

申请日：2020-05-13

Applicant: Cisco Technology, Inc.

Inventor： Xinyuan Huang ,  Johnu George ,  Marc Solanas Tarre ,  Komei Shimamura ,  Purushotham Kamath ,  Debojyoti Dutta

IPC: G06F3/06 ,  G06F9/48 ,  G06F16/25

Abstract: Aspects of the technology provide improvements to a Serverless Computing (SLC) workflow by determining when and how to optimize SLC jobs for computing in a Distributed Computing Framework (DCF). DCF optimization can be performed by abstracting SLC tasks into different workflow configurations to determined optimal arrangements for execution in a DCF environment. A process of the technology can include steps for receiving an SLC job including one or more SLC tasks, executing one or more of the tasks to determine a latency metric and a throughput metric for the SLC tasks, and determining if the SLC tasks should be converted to a Distributed Computing Framework (DCF) format based on the latency metric and the throughput metric. Systems and machine-readable media are also provided.

公开(公告)号：US20200272338A1

公开(公告)日：2020-08-27

申请号：US15931302

申请日：2020-05-13

Applicant: Cisco Technology, Inc.

Inventor： Xinyuan Huang ,  Johnu George ,  Marc Solanas Tarre ,  Komei Shimamura ,  Purushotham Kamath ,  Debojyoti Dutta

IPC: G06F3/06 ,  G06F9/48 ,  G06F16/25

Abstract: Aspects of the technology provide improvements to a Serverless Computing (SLC) workflow by determining when and how to optimize SLC jobs for computing in a Distributed Computing Framework (DCF). DCF optimization can be performed by abstracting SLC tasks into different workflow configurations to determined optimal arrangements for execution in a DCF environment. A process of the technology can include steps for receiving an SLC job including one or more SLC tasks, executing one or more of the tasks to determine a latency metric and a throughput metric for the SLC tasks, and determining if the SLC tasks should be converted to a Distributed Computing Framework (DCF) format based on the latency metric and the throughput metric. Systems and machine-readable media are also provided.