Cisco Technology, Inc.

Manikandan Kesavan

Hugo Latapie

Enzo Fenoglio

Plamen Nedeltchev

Keith Griffin

Joseph T Friel

Paul G Bright-Thomas

Eric Chen

Nathan Buckles

Monique Jeanne Morrow

Guillaume Sauvage De Saint Marc

Deon J Chatterton

Madhuri Garikapati

Eric Loyd Kroll

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.

Speaker anticipation

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.

Contextual services in a network using a deep learning agent

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.

Method and apparatus for synthesizing adaptive data visualizations

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.

Vulnerability analysis and segmentation of bring-your-own IoT devices

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.

Deep learning bias detection in text

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.

Growing community of inventors

Campbell, CA, United States of America

Manikandan Kesavan