Grégory Mermoud

Flash classification using machine learning for device classification systems

Learning and assessing device classification rules

Detecting spoofing in device classification systems

Model interpretability using proxy features

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

Extraction of prototypical trajectories for automatic classification of network KPI predictions

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

Machine learning approach for dynamic adjustment of BFD timers in SD-WAN networks

Predicting network states for answering what-if scenario outcomes

Partial reroute of traffic onto a backup tunnel using predictive routing

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

Roaming and transition patterns coding in wireless networks for cognitive visibility

Predictive routing using machine learning in SD-WANs

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

Hierarchical models using self organizing learning topologies

Active labeling of unknown devices in a network

Differentiating devices with similar network footprints using active techniques

Refinement of device classification and clustering based on policy coloring

Active learning for interactive labeling of new device types based on limited feedback

Removal of environment and local context from network traffic for device classification

Seamless rotation of keys for data analytics and machine learning on encrypted data

Learning criticality of misclassifications used as input to classification to reduce the probability of critical misclassification

Merging and optimizing heterogeneous rulesets for device classification

Using a multi-network dataset to overcome anomaly detection cold starts

Closed loop control for fixing network configuration issues to aid in device classification

Using stability metrics for live evaluation of device classification systems and hard examples collection

Sampling traffic telemetry for device classification with distributed probabilistic data structures

Cascade-based classification of network devices using multi-scale bags of network words

Traffic-based inference of influence domains in a network by using learning machines

Dynamic inspection of networking dependencies to enhance anomaly detection models in a network assurance service

Privacy-aware model generation for hybrid machine learning systems

Deep learning architecture for collaborative anomaly detection and explanation

Privacy-aware model generation for hybrid machine learning systems

ANOMALY SEVERITY SCORING IN A NETWORK ASSURANCE SERVICE

ON-PREMISE MACHINE LEARNING MODEL SELECTION IN A NETWORK ASSURANCE SERVICE

Pattern discovery from high dimensional telemetry data using machine learning in a network assurance service

DISTRIBUTED AND LEARNING MACHINE-BASED APPROACH TO GATHERING LOCALIZED NETWORK DYNAMICS

Anomaly detection with root cause learning in a network assurance service

Using machine learning based on cross-signal correlation for root cause analysis in a network assurance service

Learning internal ranges from network traffic data to augment anomaly detection systems

Dynamically adjusting prediction ranges in a network assurance system

Eliminating bad rankers and dynamically recruiting rankers in a network assurance system

Self organizing learning topologies

Hard/soft finite state machine (FSM) resetting approach for capturing network telemetry to improve device classification

Roaming and transition patterns coding in wireless networks for cognitive visibility

Predicting and forecasting roaming issues in a wireless network

Dynamic selection of models for hybrid network assurance architectures

Using random forests to generate rules for causation analysis of network anomalies

Deriving highly interpretable cognitive patterns for network assurance

Analyzing common traits in a network assurance system

TRAINING A CLASSIFIER USED TO DETECT NETWORK ANOMALIES WITH SUPERVISED LEARNING

Adaptive sampling to build accurate application throughput models

Cross-organizational network diagnostics with privacy awareness

Hierarchical models using self organizing learning topologies

Wireless throughput issue detection using coarsely sampled application activity

ADAPTIVE HEALTH STATUS SCORING FOR NETWORK ASSURANCE

Trustworthiness index computation in a network assurance system based on data source health monitoring

RESOURCE-AWARE CALL QUALITY EVALUATION AND PREDICTION

Automatic characterization of AP behaviors

Roaming and transition patterns coding in wireless networks for cognitive visibility

AUTOMATIC DETECTION OF INFORMATION FIELD RELIABILITY FOR A NEW DATA SOURCE

Sparse coding of hidden states for explanatory purposes

Mixing rule-based and machine learning-based indicators in network assurance systems

Anomaly selection using distance metric-based diversity and relevance

PREDICTING A USER EXPERIENCE METRIC FOR AN ONLINE CONFERENCE USING NETWORK ANALYTICS

Selective and dynamic application-centric network measurement infrastructure

Estimating feature confidence for online anomaly detection

Cold start mechanism to prevent compromise of automatic anomaly detection systems

Learning internal ranges from network traffic data to augment anomaly detection systems

Self organizing learning topologies

Probing technique for predictive routing in computer networks

Constraint-aware resource synchronization across hyper-distributed learning systems

Score boosting strategies for capturing domain-specific biases in anomaly detection systems

Network-based approach for training supervised learning classifiers

Distributed feedback loops from threat intelligence feeds to distributed machine learning systems

User assistance coordination in anomaly detection

Edge-based machine learning for encoding legitimate scanning

Mechanisms to prevent anomaly detectors from learning anomalous patterns

Dynamic device clustering using device profile information

Hierarchical models using self organizing learning topologies

Edge-based detection of new and unexpected flows

Detection and analysis of seasonal network patterns for anomaly detection

Merging of scored records into consistent aggregated anomaly messages

ADJUSTING ANOMALY DETECTION OPERATIONS BASED ON NETWORK RESOURCES

Anomaly detection supporting new application deployments

Anomaly detection in a network coupling state information with machine learning outputs

Cold start mechanism to prevent compromise of automatic anomaly detection systems

Network-centric visualization of normal and anomalous traffic patterns

Fingerprint merging and risk level evaluation for network anomaly detection

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

Using statistical and historical information of topology metrics in constrained networks

Data visualization in self-learning networks

Anomaly detection using network traffic data

EVENT CORRELATION IN A NETWORK MERGING LOCAL GRAPH MODELS FROM DISTRIBUTED NODES

Selectively employing dynamic traffic shaping

Selective and dynamic application-centric network measurement infrastructure

Scheduling predictive models for machine learning systems

Distributed machine learning autoscoring

Probing technique for predictive routing in computer networks