Patents by Inventor Manikandan Kesavan
Manikandan Kesavan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11019308Abstract: Systems and methods are disclosed for anticipating a video switch to accommodate a new speaker in a video conference comprising a real time video stream captured by a camera local to a first videoconference endpoint is analyzed according to at least one speaker anticipation model. The speaker anticipation model predicts that a new speaker is about to speak. Video of the anticipated new speaker is sent to the conferencing server in response to a request for the video on the anticipated new speaker from the conferencing server. Video of the anticipated new speaker is distributed to at least a second videoconference endpoint.Type: GrantFiled: November 8, 2019Date of Patent: May 25, 2021Assignee: CISCO TECHNOLOGY, INC.Inventors: Paul Bright-Thomas, Nathan Buckles, Keith Griffin, Eric Chen, Manikandan Kesavan, Plamen Nedeltchev, Hugo Mike Latapie, Enzo Fenoglio
-
Patent number: 11005965Abstract: In one embodiment, a device in a network monitors a plurality of traffic flows in the network. The device extracts a plurality of features from the monitored plurality of traffic flows. The device generates a context model by using deep learning and reinforcement learning on the plurality of features extracted from the monitored traffic flows. The device applies the context model to a particular traffic flow associated with a client, to determine a context for the particular traffic flow. The device personalizes data sent to the client from a remote source based on the determined context.Type: GrantFiled: October 29, 2019Date of Patent: May 11, 2021Assignee: Cisco Technology, Inc.Inventors: Hugo Latapie, Enzo Fenoglio, Plamen Nedeltchev, Manikandan Kesavan, Joseph Friel
-
Patent number: 10762902Abstract: A system to dynamically update presentations based on context classification of voice inputs, comprising: a storage device and a processor communicatively coupled to the storage device, wherein the processor executes application code instructions that are stored in the storage device to cause the system to: display a first graphical user interface associated with a first context via a user interface, obtain a first voice input, determine one or more first terms from the first voice input, determine that the first voice input is related to a first context based on the one or more first terms, and in response to determining that the first voice input is related to the first context: modify the first graphical user interface associated with the first context and display the modified first graphical user interface associated with the first context via the user interface.Type: GrantFiled: November 9, 2018Date of Patent: September 1, 2020Assignee: CISCO TECHNOLOGY, INC.Inventors: Madhuri Garikapati, Eric Loyd Kroll, Manikandan Kesavan
-
Patent number: 10742678Abstract: In one embodiment, a security device maintains a plurality of security enclaves for a computer network, each associated with a given level of security policies. After detecting a given device joining the computer network, the security device places the given device in a strictest security enclave of the plurality of security enclaves in response to joining the computer network. The security device then subjects the given device to joint adversarial training, where a control agent representing behavior of the given device is trained against an inciting agent, and where the inciting agent attempts to force the control agent to misbehave by applying destabilizing policies. Accordingly, the security device may determine control agent behavior during the joint adversarial training, and promotes the given device to a less strict security enclave of the plurality of enclaves in response to the control agent being robust against the attempts by the inciting agent.Type: GrantFiled: February 8, 2018Date of Patent: August 11, 2020Assignee: Cisco Technology, Inc.Inventors: Manikandan Kesavan, Plamen Nedeltchev, Hugo Latapie, Enzo Fenoglio
-
Publication number: 20200077049Abstract: Systems and methods are disclosed for anticipating a video switch to accommodate a new speaker in a video conference comprising a real time video stream captured by a camera local to a first videoconference endpoint is analyzed according to at least one speaker anticipation model. The speaker anticipation model predicts that a new speaker is about to speak. Video of the anticipated new speaker is sent to the conferencing server in response to a request for the video on the anticipated new speaker from the conferencing server. Video of the anticipated new speaker is distributed to at least a second videoconference endpoint.Type: ApplicationFiled: November 8, 2019Publication date: March 5, 2020Inventors: Paul Bright-Thomas, Nathan Buckles, Keith Griffin, Eric Chen, Manikandan Kesavan, Plamen Nedeltchev, Hugo Mike Latapie, Enzo Fenoglio
-
Publication number: 20200068041Abstract: In one embodiment, a device in a network monitors a plurality of traffic flows in the network. The device extracts a plurality of features from the monitored plurality of traffic flows. The device generates a context model by using deep learning and reinforcement learning on the plurality of features extracted from the monitored traffic flows. The device applies the context model to a particular traffic flow associated with a client, to determine a context for the particular traffic flow. The device personalizes data sent to the client from a remote source based on the determined context.Type: ApplicationFiled: October 29, 2019Publication date: February 27, 2020Inventors: Hugo Latapie, Enzo Fenoglio, Plamen Nedeltchev, Manikandan Kesavan, Joseph Friel
-
Publication number: 20190378506Abstract: A system to dynamically update presentations based on context classification of voice inputs, comprising: a storage device and a processor communicatively coupled to the storage device, wherein the processor executes application code instructions that are stored in the storage device to cause the system to: display a first graphical user interface associated with a first context via a user interface, obtain a first voice input, determine one or more first terms from the first voice input, determine that the first voice input is related to a first context based on the one or more first terms, and in response to determining that the first voice input is related to the first context: modify the first graphical user interface associated with the first context and display the modified first graphical user interface associated with the first context via the user interface.Type: ApplicationFiled: November 9, 2018Publication date: December 12, 2019Inventors: Madhuri Garikapati, Eric Loyd Kroll, Manikandan Kesavan
-
Patent number: 10498855Abstract: In one embodiment, a device in a network monitors a plurality of traffic flows in the network. The device extracts a plurality of features from the monitored plurality of traffic flows. The device generates a context model by using deep learning and reinforcement learning on the plurality of features extracted from the monitored traffic flows. The device applies the context model to a particular traffic flow associated with a client, to determine a context for the particular traffic flow. The device personalizes data sent to the client from a remote source based on the determined context.Type: GrantFiled: June 17, 2016Date of Patent: December 3, 2019Assignee: Cisco Technology, Inc.Inventors: Hugo Latapie, Enzo Fenoglio, Plamen Nedeltchev, Manikandan Kesavan, Joseph Friel
-
Patent number: 10477148Abstract: Systems and methods are disclosed for anticipating a video switch to accommodate a new speaker in a video conference comprising a real time video stream captured by a camera local to a first videoconference endpoint is analyzed according to at least one speaker anticipation model. The speaker anticipation model predicts that a new speaker is about to speak. Video of the anticipated new speaker is sent to the conferencing server in response to a request for the video on the anticipated new speaker from the conferencing server. Video of the anticipated new speaker is distributed to at least a second videoconference endpoint.Type: GrantFiled: July 11, 2017Date of Patent: November 12, 2019Assignee: CISCO TECHNOLOGY, INC.Inventors: Paul Bright-Thomas, Nathan Buckles, Keith Griffin, Eric Chen, Manikandan Kesavan, Plamen Nedeltchev, Hugo Mike Latapie, Enzo Fenoglio
-
Publication number: 20190245882Abstract: In one embodiment, a security device maintains a plurality of security enclaves for a computer network, each associated with a given level of security policies. After detecting a given device joining the computer network, the security device places the given device in a strictest security enclave of the plurality of security enclaves in response to joining the computer network. The security device then subjects the given device to joint adversarial training, where a control agent representing behavior of the given device is trained against an inciting agent, and where the inciting agent attempts to force the control agent to misbehave by applying destabilizing policies. Accordingly, the security device may determine control agent behavior during the joint adversarial training, and promotes the given device to a less strict security enclave of the plurality of enclaves in response to the control agent being robust against the attempts by the inciting agent.Type: ApplicationFiled: February 8, 2018Publication date: August 8, 2019Inventors: Manikandan Kesavan, Plamen Nedeltchev, Hugo Latapie, Enzo Fenoglio
-
Patent number: 10282414Abstract: In one embodiment, a method includes obtaining text from a user, applying the text to a deep learning neural network to generate a plurality of bias coordinates defining a point in an embedded space, and, in response to determining that at least one of the plurality of bias coordinates exceeds a threshold, providing an indication of bias to the user.Type: GrantFiled: February 28, 2017Date of Patent: May 7, 2019Assignee: Cisco Technology, Inc.Inventors: Hugo Mike Latapie, Enzo Fenoglio, Guillaume Sauvage De Saint Marc, Monique Jeanne Morrow, Manikandan Kesavan
-
Patent number: 10178131Abstract: In one embodiment, a device in a network identifies a set of network entities. The device determines characteristics of the network entities. The device assigns each of the set of network entities to one or more hyperedges of a hypergraph based on the characteristics. The device applies a security policy to a particular one of the network entities based on the one or more hyperedges of the hypergraph to which the particular network entity is assigned.Type: GrantFiled: January 23, 2017Date of Patent: January 8, 2019Assignee: Cisco Technology, Inc.Inventors: Plamen Nedeltchev, Hugo Latapie, Enzo Fenoglio, Manikandan Kesavan, Deon J. Chatterton
-
Publication number: 20180376108Abstract: Systems and methods are disclosed for anticipating a video switch to accommodate a new speaker in a video conference comprising a real time video stream captured by a camera local to a first videoconference endpoint is analyzed according to at least one speaker anticipation model. The speaker anticipation model predicts that a new speaker is about to speak. Video of the anticipated new speaker is sent to the conferencing server in response to a request for the video on the anticipated new speaker from the conferencing server. Video of the anticipated new speaker is distributed to at least a second videoconference endpoint.Type: ApplicationFiled: July 11, 2017Publication date: December 27, 2018Inventors: Paul Bright-Thomas, Nathan Buckles, Keith Griffin, Eric Chen, Manikandan Kesavan, Plamen Nedeltchev, Hugo Mike Latapie, Enzo Fenoglio
-
Publication number: 20180246873Abstract: In one embodiment, a method includes obtaining text from a user, applying the text to a deep learning neural network to generate a plurality of bias coordinates defining a point in an embedded space, and, in response to determining that at least one of the plurality of bias coordinates exceeds a threshold, providing an indication of bias to the user.Type: ApplicationFiled: February 28, 2017Publication date: August 30, 2018Inventors: Hugo Mike Latapie, Enzo Fenoglio, Guillaume Sauvage De Saint Marc, Monique Jeanne Morrow, Manikandan Kesavan
-
Publication number: 20180212996Abstract: In one embodiment, a device in a network identifies a set of network entities. The device determines characteristics of the network entities. The device assigns each of the set of network entities to one or more hyperedges of a hypergraph based on the characteristics. The device applies a security policy to a particular one of the network entities based on the one or more hyperedges of the hypergraph to which the particular network entity is assigned.Type: ApplicationFiled: January 23, 2017Publication date: July 26, 2018Inventors: Plamen Nedeltchev, Hugo Latapie, Enzo Fenoglio, Manikandan Kesavan, Deon J. Chatterton
-
Publication number: 20170366425Abstract: In one embodiment, a device in a network monitors a plurality of traffic flows in the network. The device extracts a plurality of features from the monitored plurality of traffic flows. The device generates a context model by using deep learning and reinforcement learning on the plurality of features extracted from the monitored traffic flows. The device applies the context model to a particular traffic flow associated with a client, to determine a context for the particular traffic flow. The device personalizes data sent to the client from a remote source based on the determined context.Type: ApplicationFiled: June 17, 2016Publication date: December 21, 2017Inventors: Hugo Latapie, Enzo Fenoglio, Plamen Nedeltchev, Manikandan Kesavan, Joseph Friel