Published May 1, 2021
#52 - Unadversarial Examples (Hadi Salman, MIT)
Delve into the groundbreaking world of unadversarial examples with Hadi Salman from MIT, as he elaborates on enhancing neural network robustness and transfer learning through innovative input design and understanding adversarial robustness. Discover the challenges and potential of developing more resilient AI systems and effective adversarial training for new tasks with hosts Tim Scarfe and Keith Duggar.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)
Answers 383 questions
#68 DR. WALID SABA 2.0 - Natural Language Understanding [UNPLUGGED]
Answers 383 questions
#65 Prof. PEDRO DOMINGOS [Unplugged]
Answers 383 questions
#48 Machine Learning Security - Andy Smith
Answers 383 questions
#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!
Answers 383 questions
047 Interpretable Machine Learning - Christoph Molnar
Answers 383 questions
#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).
Answers 383 questions
#56 - Dr. Walid Saba, Gadi Singer, Prof. J. Mark Bishop (Panel discussion)
Answers 383 questions
#71 - ZAK JOST (Graph Neural Networks + Geometric DL) [UNPLUGGED]
Answers 383 questions
#91 - HATTIE ZHOU - Teaching Algorithmic Reasoning via In-context Learning #NeurIPS
Answers 383 questions#88 Dr. WALID SABA - Why machines will never rule the world [UNPLUGGED]
Answers 383 questions
#109 - Dr. DAN MCQUILLAN - Resisting AI
Answers 383 questions#72 Prof. KEN STANLEY 2.0 - On Art and Subjectivity [UNPLUGGED]
Answers 383 questions
