Warming up recurrent neural networks to maximise reachable multistability greatly improves learning
- 7 August 2023
- journal article
- research article
- Published by Elsevier in Neural Networks
- Vol. 166, 645-669
Abstract
No abstract availableKeywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Minimal gated unit for recurrent neural networksInternational Journal of Automation and Computing, 2016
- Neural Networks for Sequential Data: a Pre‐training Approach based on Hidden Markov ModelsNeurocomputing, 2015
- Opening the Black Box: Low-Dimensional Dynamics in High-Dimensional Recurrent Neural NetworksNeural Computation, 2013
- Segmented-Memory Recurrent Neural NetworksIEEE Transactions on Neural Networks, 2009
- Long-term time series prediction with the NARX network: An empirical evaluationNeurocomputing, 2008
- Planning and acting in partially observable stochastic domainsArtificial Intelligence, 1998
- Long Short-Term MemoryNeural Computation, 1997
- Learning long-term dependencies in NARX recurrent neural networksIEEE Transactions on Neural Networks, 1996
- Backpropagation through time: what it does and how to do itProceedings of the IEEE, 1990
- The Optimal Control of Partially Observable Markov Processes over a Finite HorizonOperations Research, 1973