Nonlinear Time Series Analysis by Using Gamma Growing Neural Gas

11 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization (2018, methodology): “To alleviate this issue, growing self-organizing networks for temporal processing have been proposed, for instance the Gamma-GNG (Estévez and Vergara, 2012) that equips neurons with a temporal context.”
An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction (2017, background): “in time memory or recurrent connections [16], [17], [41], [42].”
Lifelong learning of human actions with deep neural network self-organization (2017, methodology): “Experiments using SOM and GNG networkswith Gamma memory showed a reduced temporal quantization error with respect to traditional context learning models for trained networks using multiple context descriptors in nonlinear time series analysis (Estévez & Hernández, 2011; Estévez & Vergara, 2012).”
Lifelong Learning of Action Representations with Deep Neural Self-Organization (2017, methodology): “Since the definition of the context descriptors is recursive, setting αw > α1 > ... > αK > 0 reduces the propagation of errors from early filter stages to higher-order contexts for other competitive networks (Estévez and Hernández 2011; Estévez and Vergara 2012).”