Time Regularization in Optimal Time Variable Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 21 references that are in the map. First posted on arXiv 28 Jun 2023.
Builds on
12 of 21 references.
References · 12
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2016Identity Mappings in Deep Residual Networkscited by 1,965
- 2017Stable Architectures for Deep Neural Networkscited by 341
- 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
- 2018Deep Neural Networks Motivated by Partial Differential Equationscited by 187
- 2019Deep learning as optimal control problems: models and numerical methodscited by 34
- 2020Fractional Deep Neural Network via Constrained Optimizationcited by 13
- 2021Novel Deep neural networks for solving Bayesian statistical inversecited by 10
- 2019Selection dynamics for deep neural networkscited by 6
- 2017Learning across scales - A multiscale method for Convolution Neural Networkscited by 5
- 2022An Optimal Time Variable Learning Framework for Deep Neural Networkscited by 3
- 2023Lecture Notes: Neural Network Architecturescited by 2
Built on by
Not cited yet.