Are All Features Created Equal? - Aleksander Madry
Offered By: Institute for Advanced Study via YouTube
Course Description
Overview
Syllabus
Intro
Machine Learning: A Success Story
Why Do We Love Deep Learning?
Key Phenomenon: Adversarial Perturbations
ML via Adversarial Robustness Lens
But: "How"/"what" does not tell us "why"
Why Are Adv. Perturbations Bad?
Human Perspective
ML Perspective
A Simple Experiment
The Robust Features Model
The Simple Experiment: A Second Look
Human vs ML Model Priors
New capability: Robustification
Some Direct Consequences
Robustness and Data Efficiency
Robustness + Perception Alignment
Robustness → Better Representations
Robustness + Image Synthesis
Problem: Correlations can be weird
Useful tool(?): Counterfactual Analysis with Robust Models
Adversarial examples arise from non-robust features in the data
Taught by
Institute for Advanced Study
Related Courses
Advanced Generative Adversarial Networks (GANs)Packt via Coursera Introducción al grabado ilustrado con Procreate
Domestika Ilustración Editorial
Domestika Image Generation with Imagen
Pluralsight AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
University of Central Florida via YouTube