A general learning rate improvement strategy for deep neural networks training
Open Access
- 31 January 2026
- journal article
- research article
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 12 (3)
Abstract
No abstract availableKeywords
This publication has 19 references indexed in Scilit:
- State filtered disturbance rejection controlNonlinear Dynamics, 2024
- AMAdam: adaptive modifier of Adam methodKnowledge and Information Systems, 2024
- Multilayer neurocontrol of high‐order uncertain nonlinear systems with active disturbance rejectionInternational Journal of Robust and Nonlinear Control, 2024
- MLR-SNet: Transferable LR Schedules for Heterogeneous TasksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Appropriate Learning Rates of Adaptive Learning Rate Optimization Algorithms for Training Deep Neural NetworksIEEE Transactions on Cybernetics, 2021
- Automatic, dynamic, and nearly optimal learning rate specification via local quadratic approximationNeural Networks, 2021
- Learning the Step-size Policy for the Limited-Memory Broyden-Fletcher-Goldfarb-Shanno Algorithm2021
- Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks2019
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Practical Recommendations for Gradient-Based Training of Deep Architectures2012