Grégory Mermoud

Flash classification using machine learning for device classification systems

Detection of isolated changes in network metrics using smart-peering

Adaptive training of machine learning models based on live performance metrics

Learning and assessing device classification rules

Detecting spoofing in device classification systems

Revisiting device classification rules upon observation of new endpoint attributes

Model interpretability using proxy features

Peer-to-peer feature exchange for edge inference of forecasting models

Unsupervised learning of local-aware attribute relevance for device classification and clustering

Protecting device classification systems from adversarial endpoints

Extraction of prototypical trajectories for automatic classification of network KPI predictions

Forecasting network KPIs

Anomaly detection of model performance in an MLOps platform

Predicting the impact of network software upgrades on machine learning model performance

Event-triggered machine learning for rare event forecasting in a software defined wide area Network (SD-WAN)

Assessing data fidelity in a machine learning-based network assurance system

Per-flow call admission control using a predictive model to estimate tunnel QoS in SD-WAN networks

Predicting network states for answering what-if scenario outcomes

Device type classification using metric learning in weakly supervised settings

Preserving privacy in exporting device classification rules from on-premise systems

Ensuring backup path performance for predictive routing in SD-WANs

Adaptive stress testing of SD-WAN tunnels for what-if scenario model training

Progressive refinement of device classifications using colored device and policy trees

Detection and resolution of rule conflicts in device classification systems

Partial reroute of traffic onto a backup tunnel using predictive routing

Continuous validation of active labeling for device type classification

Intelligent tunnel assignment and dynamic SLA threshold configuration to increase availability and utilization of SD-WAN tunnels

Machine learning driven data collection of high-frequency network telemetry for failure prediction

Piggybacking control and data plane telemetry for machine learning-based tunnel failure prediction

Tracking of devices across MAC address updates

Adaptive threshold selection for SD-WAN tunnel failure prediction

Learning stable representations of devices for clustering-based device classification systems

Predictive routing using machine learning in SD-WANs

Root cause analysis of seasonal service level agreement (SLA) violations in SD-WAN tunnels

Active labeling of unknown devices in a network

PEER COMPARISON BY A NETWORK ASSURANCE SERVICE USING NETWORK ENTITY CLUSTERS

Merging and optimizing heterogeneous rulesets for device classification

Privacy-aware model generation for hybrid machine learning systems

Hierarchical models using self organizing learning topologies

Roaming and transition patterns coding in wireless networks for cognitive visibility

Warm-start with knowledge and data based grace period for live anomaly detection systems

Data visualization in self-learning networks