Adversarial Examples Explained
Laurens discusses the concept of adversarial examples, where subtle changes to an image can drastically alter a machine learning model's predictions. He highlights a study revealing that image recognition models perform better in Western countries, indicating a lack of understanding of global diversity. This insight prompts a shift in focus towards addressing broader issues in AI, such as relevance and ethical considerations, emphasizing the importance of community collaboration in improving these technologies.In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
709: Big A.I. R&D Risks Reap Big Societal Rewards — with Meta's Dr. Laurens van der Maaten
Related Questions