On a single task, deep neural networks can learn a wide range of solutions, depending on their optimizer, training data, architecture, and hyperparameters. Many of these solutions are surprisingly mode-connected: rather than isolated points in the weight space, they are connected by low loss regions. Despite this obser...
Ann C. Huang, Mitchell Ostrow, Zhou-Yang Lu et al.· arXiv.org· 0 citations
Comparisons are fundamental to science: experiment against model, one organism against another, a system against itself across time. Because many systems, from brains to climate, are characterized by how they evolve in time, it is a natural goal to compare their dynamics. Dynamical systems comparison is well defined, b...
Mitchell Ostrow, Adam J. Eisen, L. Kozachkov et al.· bioRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.