Dynamic Meta-Learning for Anomaly Detection - Cole Sodja, Microsoft Defender ATP
Offered By: Alan Turing Institute via YouTube
Course Description
Overview
Explore a methodology for measuring probabilistic calibration and dynamically updating scores in anomaly detection systems. Delve into the challenges faced by Microsoft Defender Advanced Threat Protection in monitoring billions of anomaly detectors across diverse data sources. Learn about adaptive mixtures of functional inflated beta-binomial models and their application in identifying and updating scores for cyber indicators of attack. Discover how an automated statistical diagnostics system can infer optimal weighting of anomaly scores through probabilistic inference, addressing the scalability issues of manual detector review. Cover topics such as p-value calibration, model uncertainty, meta-learning, Bayesian approaches, state-space models, filtering, and probability distribution modeling in this comprehensive 1-hour 26-minute talk by Cole Sodja from Microsoft Defender ATP, presented at the Alan Turing Institute.
Syllabus
Introduction
Agenda
Motivation
Calibration
Pvalue calibration
Model uncertainty
What is calibration
MetaLearning
Bayesian Approach
Monitoring
Statespace Models
Filtering
Modeling
Probability distribution
Wrap up
Taught by
Alan Turing Institute
Related Courses
Model Building and ValidationAT&T via Udacity Поиск структуры в данных
Moscow Institute of Physics and Technology via Coursera Data Analytics Foundations for Accountancy II
University of Illinois at Urbana-Champaign via Coursera Developing Machine Learning Applications
Amazon via Independent Anomaly Detection in Time Series Data with Keras
Coursera Project Network via Coursera