Patents by Inventor Pierre A. Andre

Pierre A. Andre 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).

  • Predicting the impact of network software upgrades on machine learning model performance
    Patent number: 11409516
    Abstract: In one embodiment, a service receives software version data regarding versions of software executed by devices in a network. The service detects a version change in the version of software executed by one or more of the devices, based on the received software version data. The service makes a determination that a drop in data quality of input data for a machine learning model used to monitor the network is associated with the detected version change. The service reverts the one or more devices to a prior version of software, based on the determination that the drop in quality of the input data for the machine learning model used to monitor the network is associated with the detected version change.
    Type: Grant
    Filed: December 10, 2019
    Date of Patent: August 9, 2022
    Assignee: Cisco Technology, Inc.
    Inventors: Vinay Kumar Kolar, Jean-Philippe Vasseur, Grégory Mermoud, Pierre-Andre Savalle
  • Artificial neutral network precoding for massive MIMO systems
    Patent number: 11411794
    Abstract: A method and apparatus for artificial neural network precoding for massive MIMO systems are disclosed. In one embodiment, a method includes processing, by an artificial neural network, ANN, precoding engine, at least one input signal by 5 performing a low peak-to-average-power ratio, PAPR, precoding on the at least one input signal; and transmitting, via at least one antenna array having at least one antenna, at least one precoded output signal processed by the ANN precoding engine.
    Type: Grant
    Filed: March 15, 2019
    Date of Patent: August 9, 2022
    Assignee: Telefonaktiebolaget LM Ericsson (publ)
    Inventors: Bilel Fehri, Pierre-Andre Laporte, Mark Edward Rollins
  • Adaptive stress testing of SD-WAN tunnels for what-if scenario model training
    Patent number: 11411838
    Abstract: In one embodiment, a service in a network computes an expected information gain associated with rerouting traffic from a first tunnel onto a backup tunnel in the network. The service initiates, based on the expected information gain, rerouting of the traffic from the first tunnel onto the backup tunnel. The service obtains performance measurements for the traffic rerouted onto the backup tunnel. The service uses the performance measurements to train a machine learning model to predict whether rerouting traffic from the first tunnel onto the backup tunnel will satisfy a service level agreement (SLA) of the traffic.
    Type: Grant
    Filed: May 29, 2019
    Date of Patent: August 9, 2022
    Assignee: Cisco Technology, Inc.
    Inventors: Jean-Philippe Vasseur, Grégory Mermoud, Pierre-Andre Savalle, Vinay Kumar Kolar
  • Roaming and transition patterns coding in wireless networks for cognitive visibility
    Patent number: 11405802
    Abstract: In one embodiment, a device receives data regarding usage of access points in a network by a plurality of clients in the network. The device maintains an access point graph that represents the access points in the network as vertices of the access point graph. The device generates, for each of the plurality of clients, client trajectories as trajectory subgraphs of the access point graph. A particular client trajectory for a particular client comprises a set of edges between a subset of the vertices of the access point graph and represents transitions between access points in the network performed by the particular client. The device identifies a transition pattern from the client trajectories by deconstructing the trajectory subgraphs. The device uses the identified transition pattern to effect a configuration change in the network.
    Type: Grant
    Filed: June 18, 2020
    Date of Patent: August 2, 2022
    Assignee: Cisco Technology, Inc.
    Inventors: Pierre-André Savalle, Grégory Mermoud, Jean-Philippe Vasseur, Javier Cruz Mota
  • Revisiting device classification rules upon observation of new endpoint attributes
    Patent number: 11399023
    Abstract: In various embodiments, a device classification service uses an initial device classification rule to label each of a set of endpoint devices in a network as being of a particular device type. The device classification service identifies a particular attribute exhibited by at least a portion of the set of endpoint devices and was not previously used to generate the initial device classification rule. The device classification service generates one or more new device classification rules based in part on the particular attribute. The device classification service switches from using the initial device classification rule to label endpoint devices in the network to using the one or more new device classification rules to label endpoint devices in the network.
    Type: Grant
    Filed: April 21, 2020
    Date of Patent: July 26, 2022
    Assignee: Cisco Technology, Inc.
    Inventors: Jean-Philippe Vasseur, Pierre-André Savalle, Grégory Mermoud, David Tedaldi
  • Assessing data fidelity in a machine learning-based network assurance system
    Patent number: 11397876
    Abstract: In one embodiment, a service computes a data fidelity metric for network telemetry data used by a machine learning model to monitor a computer network. The service detects unacceptable performance of the machine learning model. The service determines a correlation between the data fidelity metric and the unacceptable performance of the machine learning model. The service adjusts generation of the network telemetry data for input to the machine learning model, based on the determined correlation between the data fidelity metric and the unacceptable performance of the machine learning model.
    Type: Grant
    Filed: November 22, 2019
    Date of Patent: July 26, 2022
    Assignee: Cisco Technology, Inc.
    Inventors: Jean-Philippe Vasseur, Vinay Kumar Kolar, Andrea Di Pietro, Grégory Mermoud, Pierre-Andre Savalle
  • Wheelchair footrest assembly
    Patent number: 11389351
    Abstract: A footrest assembly for wheelchair of the type having a structure expandable from a contracted condition to an expanded position comprises a beam assembly having a structural member having a first end and a second end. A first joint one or more rotational degrees of freedom is adapted to interface the first end of the structural member to a first side of a frame of the wheelchair. A linkage assembly is connected to the structural member by a central joint with one or more rotational degrees of freedom and a lockable translational degree of freedom joint. A second joint with one or more rotational degrees of freedom is adapted to interface the linkage assembly to a second side of the frame of the wheelchair. A connector interface releasably engages the beam assembly to the linkage assembly and/or to the second joint when the wheelchair is deployed for use.
    Type: Grant
    Filed: June 26, 2019
    Date of Patent: July 19, 2022
    Assignee: MOTION COMPOSITES INC.
    Inventors: Pierre-Andre Couture, Maxime Lamarre, Gabriel Feron, Michael Archambault
  • DISTORTION DETECTION WITH MULTIPLE ANTENNAS
    Publication number: 20220224423
    Abstract: A method in a network node and an apparatus for determining passive intermodulation (PIM) characteristics at the network node are provided. According to one aspect, a method includes capturing signals from each of at least one antenna port at a first time and a second time. The method includes determining a first covariance matrix based on signals captured at the first time. The method also includes determining a second covariance matrix based on signals captured at the second time. The method further includes determining a difference matrix, the difference matrix being based on a difference between the first and second covariance matrices, the difference matrix corresponding to changes in PIM between the first time and the second time.
    Type: Application
    Filed: July 17, 2019
    Publication date: July 14, 2022
    Inventors: Mark WYVILLE, Pierre-Andre LAPORTE
  • Detection of isolated changes in network metrics using smart-peering
    Patent number: 11381640
    Abstract: In one embodiment, a network assurance service that monitors one or more networks identifies changes in a key performance indicator for each of a plurality of network entities in the one or more networks. The service forms a peer group of network entities from the plurality of network entities whose changes in the key performance indicator are correlated. The service monitors the key performance indicator for network entities in the peer group of network entities. The service, based on the monitoring, detects an anomalous change in the key performance indicator for a particular network entity in the peer group of network entities relative to other network entities in the peer group of network entities.
    Type: Grant
    Filed: May 15, 2020
    Date of Patent: July 5, 2022
    Assignee: Cisco Technology, Inc.
    Inventors: Pierre-André Savalle, Jean-Philippe Vasseur, Grégory Mermoud, Vinay Kumar Kolar
  • METHOD FOR DETERMINING THE POSITION OF THE COMPLETELY ISOLATED REGIME OF A SPIN QUBIT AND METHOD FOR MANIPULATING AT LEAST ONE SPIN QUBIT
    Publication number: 20220199889
    Abstract: A method for manipulating a group of quantum dots of a quantum dots matrix, called target group, each target group including a quantum dot and containing a charged particle, the matrix being connected to a reservoir of charged particles, each target group being defined by a potential barrier, each charged particle being a carrier of a charge and spin, the method including, for each target group, a total isolation procedure of the target group relative to the other quantum dots, the potential barrier separating the target group of quantum dots of the matrix adjacent to the target group being configured so that the charged particle(s) contained in the target group cannot cross the potential barrier in order to be moved to the adjacent quantum dots or to the reservoir even when such a transition is authorised from an energy standpoint; and maintaining the target group in the completely isolated regime.
    Type: Application
    Filed: December 23, 2021
    Publication date: June 23, 2022
    Inventors: Pierre-André MORTEMOUSQUE, Tristan MEUNIER, Benoit BERTRAND, Baptiste JADOT, Matias URDAMPILLETA
  • METHOD FOR READING THE SPIN STATE OF A SYSTEM AND ASSOCIATED METHOD FOR DETERMINING THE FIDELITY
    Publication number: 20220198314
    Abstract: A method of measuring the spin state of two charged particles able to adopt a first, second, third, and fourth spin state S, T+, T0 and T, the two charged particles being contained in a system, including first and second quantum dots characterised by a first parameter ? relative to the potential barrier separating the two quantum dots and a second parameter ? corresponding to the difference in energy between the fundamental states of the first and second quantum dots, the couple formed by the values of these two parameters defining an operating point of the system as a function of which the system adopts a first charge state noted (1,1) wherein each quantum dot contains a charged particle, a second charge state noted (2,0) wherein the first quantum dot contains two charged particles or a third charge state noted (0,2) wherein the second quantum dot contains two charged particles.
    Type: Application
    Filed: December 23, 2021
    Publication date: June 23, 2022
    Inventors: Pierre-André MORTEMOUSQUE, Baptiste JADOT, Tristan MEUNIER, Matias URDAMPILLETA
  • COEFFICIENT SOLUTION FOR LOW PEAK-TO-AVERAGE POWER RATIO (PAPR) PRECODERS
    Publication number: 20220182112
    Abstract: A network node is provided. The network node includes processing circuitry configured to determine at least one Convex Reduction of Amplitude, CRAM, projection matrix based at least in part on a signal subspace of scheduled wireless devices, and optionally cause transmission based at least in part on the at least one CRAM projection matrix.
    Type: Application
    Filed: May 1, 2019
    Publication date: June 9, 2022
    Inventor: Pierre-Andre LAPORTE
  • Flash classification using machine learning for device classification systems
    Patent number: 11349716
    Abstract: In various embodiments, a device classification service makes a determination that an endpoint device in a network is eligible for expedited device classification based on a policy. The device classification service obtains, after making the determination that the endpoint device in the network is eligible for expedited device classification, telemetry data regarding the endpoint device generated by actively probing the endpoint device. The device classification service determines whether the telemetry data regarding the endpoint device matches any existing device classification rules. The device classification service generates, based on the telemetry data, a device classification rule that assigns a device type to the endpoint device, when the telemetry data does not match any existing device classification rules.
    Type: Grant
    Filed: May 20, 2020
    Date of Patent: May 31, 2022
    Assignee: Cisco Technology, Inc.
    Inventors: Jean-Philippe Vasseur, Grégory Mermoud, Pierre-André Savalle, David Tedaldi
  • LEARNING ROBUST AND ACCURATE RULES FOR DEVICE CLASSIFICATION FROM CLUSTERS OF DEVICES
    Publication number: 20220166675
    Abstract: In various embodiments, a device classification service obtains traffic telemetry data for a plurality of devices in a network. The service applies clustering to the traffic telemetry data, to form device clusters. The service generates a device classification rule based on a particular one of the device clusters. The service receives feedback from a user interface regarding the device classification rule. The service adjusts the device classification rule based on the received feedback.
    Type: Application
    Filed: October 29, 2021
    Publication date: May 26, 2022
    Inventors: David Tedaldi, Grégory Mermoud, Pierre-André Savalle, Jean-Philippe Vasseur
  • EIGENVALUE-BASED PASSIVE INTERMODULATION DETECTION
    Publication number: 20220149889
    Abstract: A method and network node for detection of passive intermodulation (PIM) are disclosed. According to one aspect, a method includes determining values of a covariance matrix based at least in part on uplink signals received by the network node radio. The method also includes determining a plurality of uplink (UL) channel 5 eigenvalues based at least in part on an eigen-component acquisition technique. The method further includes determining a presence or absence of PIM based at least in part on a plurality of the UL channel eigenvalues.
    Type: Application
    Filed: April 9, 2019
    Publication date: May 12, 2022
    Inventors: Pierre-Andre LAPORTE, Mark WYVILLE, Bilel FEHRI
  • Anomaly detection of model performance in an MLOps platform
    Patent number: 11310141
    Abstract: In one embodiment, a service tracks performance of a machine learning model over time. The machine learning model is used to monitor one or more computer networks based on data collected from the one or more computer networks. The service also tracks performance metrics associated with training of the machine learning model. The service determines that a degradation of the performance of the machine learning model is anomalous, based on the tracked performance of the machine learning model and performance metrics associated with training of the model. The service initiates a corrective measure for the degradation of the performance, in response to determining that the degradation of the performance is anomalous.
    Type: Grant
    Filed: December 11, 2019
    Date of Patent: April 19, 2022
    Assignee: Cisco Technology, Inc.
    Inventors: Vinay Kumar Kolar, Jean-Philippe Vasseur, Grégory Mermoud, Pierre-Andre Savalle
  • Radiation pattern modification in the presence of interference sources in frequency division duplex (FDD) systems
    Patent number: 11303337
    Abstract: A first radio node including processing circuitry configured to configure the first radio node to: obtain a first interference subspace, obtain beamforming weights based on the first interference subspace where the beamforming weights configured to modify a radiation pattern in at least one communication direction of at least one interference source, and perform wireless communications based on the beamforming weights.
    Type: Grant
    Filed: May 16, 2018
    Date of Patent: April 12, 2022
    Assignee: Telefonaktiebolaget LM Ericsson (publ)
    Inventors: Alex Stephenne, Pierre-Andre Laporte, Mark William Wyville
  • Continuous validation of active labeling for device type classification
    Patent number: 11297079
    Abstract: In one embodiment, a device classification service forms a device cluster by applying clustering to telemetry data associated with a plurality of devices. The service obtains device type labels for the device cluster. The service generates a device type classification rule using the device type labels and the telemetry data. The service determines whether the device type classification rule should be revalidated by applying a revalidation policy to the device type classification rule. The service revalidates the device type classification rule, based on a determination that the device type classification rule should be revalidated.
    Type: Grant
    Filed: May 6, 2019
    Date of Patent: April 5, 2022
    Assignee: Cisco Technology, Inc.
    Inventors: Jean-Philippe Vasseur, Pierre-Andre Savalle, Grégory Mermoud, David Tedaldi
  • SYSTEMS AND METHODS FOR ENFORCING CONSTRAINTS TO PREDICTIONS
    Publication number: 20220101162
    Abstract: There is disclosed a method and system for determining states satisfying one or more constraints. The method comprises inputting, to a machine learning algorithm (MLA), input data. The MLA outputs a probability distribution. The probability distribution comprises a predicted probability for each of a plurality of pairs, where each pair comprises a class in a set of classes and a corresponding state of the MLA. The states of the probability distribution are added to a set of states to be searched. States that are end states or that fail to satisfy at least one of the constraints are removed from the set of states to be searched. One or more of the set of states to be searched are input to the MLA. The search is repeated with new states output by the MLA. End states output by the MLA may be output as output states.
    Type: Application
    Filed: September 29, 2020
    Publication date: March 31, 2022
    Inventors: Hector PALACIOS, Pierre-Andre NOEL
  • SYSTEMS AND METHODS FOR ENFORCING CONSTRAINTS IN CHARACTER RECOGNITION
    Publication number: 20220101036
    Abstract: There is disclosed a method of and a system for predicting text in an image using one or more constraints. The image is input to a machine learning algorithm (MLA). The MLA outputs a probability distribution. The probability distribution comprises a predicted probability for each of a plurality of pairs, where each pair comprises a class and a next state of the MLA. The states of the probability distribution are added to a set of states to be searched. States that are end states or that fail to satisfy at least one of the constraints are removed from the set of states to be searched. States of the set of states to be searched are input to the MLA. The search is repeated with new states output by the MLA. End states output by the MLA are output as output states that each comprise a sequence of characters.
    Type: Application
    Filed: September 29, 2020
    Publication date: March 31, 2022
    Inventors: Hector PALACIOS, Pierre-Andre NOEL