WeightWatcher is based on theoretical research (done injoint with UC Berkeley) into Why Deep Learning Works, based on our Theory of Heavy Tailed Self-Regularization (HT-SR). It uses ideas from Random Matrix Theory (RMT), Statistical Mechanics, and Strongly Correlated Systems.
Check out the full article at KDNuggets.com website
How to Determine if Your Machine Learning Model is Overtrained
Check out the full article at KDNuggets.com website
How to Determine if Your Machine Learning Model is Overtrained
Comments
Post a Comment