Trust in AI
Moustapha shares his journey into AI, sparked by a university project, and discusses his current focus on trust in AI. He highlights the importance of safety, fairness, and interpretability, emphasizing the challenges posed by adversarial examples and the biases found in popular datasets like ImageNet. His research aims to enhance the robustness of AI systems and address the underlying issues of biased decision-making.In this clip
From this podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Security and Safety in AI: Adversarial Examples, Bias and Trust with Moustapha Cissé - #108
Related Questions
Are there biases in AI as discussed in the episode Richard Socher — The Challenges of Making ML Work in the Real World and the clip Addressing AI Bias?
Are there biases in AI as discussed in the episode Understanding AI’s Threats and Opportunities — with Mo Gawdat and the clip Systemic Bias Uncovered, as well as in the episode The Surprising Ways Algorithms Steer Your Life & How to Make Your Ideas Stick and the clip Algorithmic Bias Debate?
Are there biases in AI as discussed in the episode Protecting Society From AI Harms: Amnesty International’s Matt Mahmoudi and Damini Satija (Part One) and the clip Technological Fixes, as well as in the episode The Surprising Ways Algorithms Steer Your Life & How to Make Your Ideas Stick and the clip Algorithmic Bias Debate?