Time Regularization in Optimal Time Variable Learning

Author name not available (Why is that?)

Publication date: 28 June 2023

Abstract: Recently, optimal time variable learning in deep neural networks (DNNs) was introduced in arXiv:2204.08528. In this manuscript we extend the concept by introducing a regularization term that directly relates to the time horizon in discrete dynamical systems. Furthermore, we propose an adaptive pruning approach for Residual Neural Networks (ResNets), which reduces network complexity without compromising expressiveness, while simultaneously decreasing training time. The results are illustrated by applying the proposed concepts to classification tasks on the well known MNIST and Fashion MNIST data sets. Our PyTorch code is available on https://github.com/frederikkoehne/time_variable_learning.

Has companion code repository: https://github.com/frederikkoehne/time_variable_learning

This page was built for publication: Time Regularization in Optimal Time Variable Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6441801)