Published Jul 11, 2020
GANs Can Be Interpretable
Erik Härkönen delves into the interpretability of GANs, unveiling innovative techniques for image manipulation through Principal Component Analysis, and discussing the challenges and potential of creating user-friendly interfaces for these powerful technologies, amidst the growing implications of deep fakes.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
GANs in Finance
Answers 383 questions
Multi-Agent Diverse Generative Adversarial Networks
Answers 383 questions
Black Boxes Are Not Required
Answers 383 questions
Visualization and Interpretability
Answers 383 questions
Interpretability Practitioners
Answers 383 questions
Interpretability
Answers 383 questions[MINI] Generative Adversarial Networks
Answers 383 questions
Interpretable One Shot Learning
Answers 383 questions
Interpretability Tooling
Answers 383 questions
Machine Learning on Images with Noisy Human-centric Labels
Answers 383 questions
Fooling Computer Vision
Answers 383 questions
Self-Explaining AI
Answers 383 questions
Visual Illusions Deceiving Neural Networks
Answers 383 questions
Adversarial Explanations
Answers 383 questions
Defending Against Adversarial Attacks
Answers 383 questions