Dimensionality Phase Shift
Yannic and Connor discuss the potential phase shift in machine learning systems with higher dimensional inputs and increased data scaling. They explore the idea of systems transitioning from interpolating training data to introspection and expressiveness, challenging the notion of qualitative shifts solely based on scaling up.In this clip
From this podcast
Machine Learning Street Talk (MLST)
ICLR 2020: Yoshua Bengio and the Nature of Consciousness
Related Questions