Neural Network Evolution
Simon introduces the concept of centered kernel alignment to analyze self similarity in neural networks, revealing the halting of evolution and over parameterization. Tim shares insights on using self similarity matrices to understand representation evolution in music tracks, showcasing symmetries and unique patterns.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!
Related Questions