Trainer posts for every online training module at NTHRYS. Open a post to see what the trainer does, then apply.
10,000+ trainer posts · page 475 of 500
Prepare features so oncology anomaly detection draws on clean relevant patient and imaging data.
Curate developmental anomaly image datasets for detection models.
Report investigated anomalies and their causes for the team.
Learn to route anomalies for investigation and document the outcome.
Validate anomaly models and report detection performance to stakeholders.
Validate anomaly detection models against known process events.
Learn to feed scouting outcomes back to improve anomaly detection.
Configure dashboards that present flagged anomalies with context for efficient clinical and audit review.
Design review workflows that feed confirmed anomalies back into model improvement.
Design anomaly scoring models for network security monitoring data.
Set anomaly thresholds that balance sensitivity and false alarms.
Tune anomaly thresholds so logistics anomaly detection balances sensitivity and false alarms.
Learn to define point, contextual and collective anomalies and what each detector targets.
Share data into benchmarking schemes without exposing identifiable farm detail.
Anonymise and pseudonymise biosignal and video data while keeping utility.
Assess whether anonymised clinical data could still identify a patient.
Assess anonymisation and re identification risk for graph data.
Apply anonymisation techniques to diagnostic data in the diagnostics clinic workflow.
Anonymise and protect neural datasets while keeping them useful.
Anonymise clinical datasets for sharing and transparency needs.
Only the first 10,000 are listed. Pick a field or add keywords to find the rest.