A global-local hybrid Evolutionary Strategy (ES) for Recurrent Neural Networks (RNNs) in system identification

Abstract

Recurrent neural networks, through their unconstrained synaptic connectivity and resulting state-dependent nonlinear dynamics, offer a greater level of computational ability when compared with regular feedforward neural network (FFNs) architectures. A necessary consequence of this increased capability is a higher degree of complexity, which in turn leads to… (More)
DOI: 10.1109/CEC.2007.4424668

4 Figures and Tables

Topics

  • Presentations referencing similar topics