1 code implementation • 6 Mar 2017 • Eldad Haber, Lars Ruthotto, Elliot Holtham, Seong-Hwan Jun
In this work we establish the relation between optimal control and training deep Convolution Neural Networks (CNNs).
no code implementations • NeurIPS 2012 • Seong-Hwan Jun, Liangliang Wang, Alexandre Bouchard-Côté
We propose a novel method for scalable parallelization of SMC algorithms, Entangled Monte Carlo simulation (EMC).