Generalization in fully-connected neural networks for time series forecasting
- 1 September 2019
- journal article
- research article
- Published by Elsevier BV in Journal of Computational Science
- Vol. 36, 101020
- https://doi.org/10.1016/j.jocs.2019.07.007
Abstract
No abstract availableKeywords
This publication has 10 references indexed in Scilit:
- Robust Large Margin Deep Neural NetworksIEEE Transactions on Signal Processing, 2017
- Generalization bounds for non-stationary mixing processesMachine Learning, 2016
- Random Matrices and Complexity of Spin GlassesCommunications on Pure and Applied Mathematics, 2012
- The Generalization Ability of Online Algorithms for Dependent DataIEEE Transactions on Information Theory, 2012
- Supervised Sequence Labelling with Recurrent Neural NetworksPublished by Springer Science and Business Media LLC ,2012
- Replica Symmetry Breaking Condition Exposed by Random Matrix Calculation of Landscape ComplexityJournal of Statistical Physics, 2007
- Statistics of Critical Points of Gaussian Fields on Large-Dimensional SpacesPhysical Review Letters, 2007
- A Quantitative Study of Fault Tolerance, Noise Immunity, and Generalization Ability of MLPsNeural Computation, 2000
- Forecasting with artificial neural networks:: The state of the artInternational Journal of Forecasting, 1998
- Flat MinimaNeural Computation, 1997