Evolving Connectionist Systems: The Knowledge Engineering Approach

331 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.

The Super-Turing Computational Power of plastic Recurrent Neural Networks (2014, background): “In the context of Artificial Intelligence (AI), the consideration of evolving neural architectures in socalled Evolving Connectionist Systems (ECoS) has proven to be fruitful and significantly increased in applications.(6,7) Yet from a theoretical perspective, the general concepts of evolvability an”
Detecting concept drift in data streams using model explanation (2018, background): “C E A notable group of methods are evolving learners, which continually develop their structure, functionality and internal knowledge representation through learning and interacting with the environment (Angelov et al., 2010; Lughofer, 2011; Kasabov, 2007).”
Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition. (2013, methodology): “This idea was used in a class of SNN, called evolving SNN (eSNN) (Kasabov, 2007; Wysoski et al., 2010).”
NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data (2014, unknown): “The second approach does not exclude using evolutionary computation to optimize the GRN as it is the case in the CNGM simulator (Kasabov, 2007; Wysoski et al., 2010).”