Gamma-Filter Self-Organizing Neural Networks for Time Series Analysis

8 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 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).”
Nonlinear Time Series Analysis by Using Gamma Growing Neural Gas (2012, methodology): “In our previous work we have added Gamma filters [9] to SOM, NG and GNG, yielding the γ-SOM [10], γ-NG [11], and γ-GNG models [12], respectively.”