Learning Representations Dynamically
Simon discusses the mystery behind learning representations in neural networks, exploring the dynamics that prevent collapsing to trivial solutions. The conversation delves into the complexities of matching network representations and the enigmatic success of methods like BYOL.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!
Related Questions