Crumpled Spaces in Analysis
Pavan discusses the importance of geometric principles in machine learning, emphasizing that raw observational data should be analyzed in a "crumpled" space. He highlights the relevance of mathematics from the past two centuries, particularly geometry, topology, and group theory, which have yet to be systematically integrated into the field. This approach allows for a deeper understanding of problem specifics through the lens of advanced mathematical concepts.In this clip
From this podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Invariance, Geometry and Deep Neural Networks with Pavan Turaga - #386 (Video)
Related Questions