Interpretable Active Learning
Offered By: Association for Computing Machinery (ACM) via YouTube
Course Description
Overview
Explore an insightful conference talk on interpretable active learning presented by Richard Phillips at FAT* 2018. Delve into the innovative approach that combines active learning with LIME (Local Interpretable Model-agnostic Explanations) to enhance model interpretability. Discover how this method can improve the efficiency and transparency of machine learning models. Learn about the formula behind this technique and its potential applications in various fields. Gain valuable insights from the presentation's conclusion and engage with the thought-provoking questions raised during the discussion.
Syllabus
Introduction
Title
Lime
Formula
Conclusion
Questions
Taught by
ACM FAccT Conference
Related Courses
Introduction to Artificial IntelligenceStanford University via Udacity Natural Language Processing
Columbia University via Coursera Probabilistic Graphical Models 1: Representation
Stanford University via Coursera Computer Vision: The Fundamentals
University of California, Berkeley via Coursera Learning from Data (Introductory Machine Learning course)
California Institute of Technology via Independent