This course focuses on the topic of fair deep anomaly detection. The learning outcomes include understanding the Deep SVDD method, learning about the 80 Rule, and exploring a proposed framework for anomaly detection. The course teaches skills such as adversarial learning, minimizing adversarial loss, pipeline development, and extensions. The teaching method involves presenting research findings, experimental results, and a summary of the proposed framework. The intended audience for this course is individuals interested in anomaly detection, deep learning, and fairness in machine learning algorithms.
Overview
Syllabus
Introduction
Deep SVDD
Anonymity Detection
Outline
The 80 Rule
Proposed Framework
adversarial learning
minimizing adversarial loss
pipeline
extensions
Experiments
Results
Experimental Results
Summary
Taught by
ACM FAccT Conference
Related Courses
-
Master of Machine Learning and Data Science
-
Introduction to Deep Learning
3.7 -
PyTorch for Deep Learning & Machine Learning – Full Course
-
KDD 2020: Robust Deep Learning Methods for Anomaly Detection
-
Deep Learning for Anomaly Detection - Expanding Our Marker Vocabulary
-
Generative Adversarial Minority Oversampling
