Published Aug 22, 2024
Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)
MIT PhD student Andrew Ilyas delves into the vulnerabilities of neural networks through adversarial examples, examines biases in data collection and their impact on machine learning, and presents innovative data modeling methods like TRAK to enhance prediction accuracy.
Topics covered
Popular Clips
Questions from this episode
- Asked by 32 people
- Asked by 21 people
- Asked by 18 people
- Asked by 1 person
Episode Highlights
Related Episodes
#52 - Unadversarial Examples (Hadi Salman, MIT)
Answers 383 questions
#48 Machine Learning Security - Andy Smith
Answers 383 questions
The Elegant Math Behind Machine Learning - Anil Ananthaswamy
Answers 383 questions
Explainability, Reasoning, Priors and GPT-3
Answers 383 questions
047 Interpretable Machine Learning - Christoph Molnar
Answers 383 questions
Prof. Melanie Mitchell 2.0 - AI Benchmarks are Broken!
Answers 383 questions
Jordan Edwards: ML Engineering and DevOps on AzureML
Answers 383 questions
#74 Dr. ANDREW LAMPINEN - Symbolic behaviour in AI [UNPLUGGED]
Answers 383 questions
#73 - YASAMAN RAZEGHI & Prof. SAMEER SINGH - NLP benchmarks
Answers 383 questions
Computation, Bayesian Model Selection, Interactive Articles
Answers 383 questions
Nicholas Carlini (Google DeepMind)
Answers 383 questions#57 - Prof. Melanie Mitchell - Why AI is harder than we think
Answers 383 questions
It's Not About Scale, It's About Abstraction - Francois Chollet
Answers 383 questions
Can we build a generalist agent? Dr. Minqi Jiang and Dr. Marc Rigter
Answers 383 questions
