Abstract: The idea of Reservoir Computing has become so popular recently due to its computational efficiency and the fact that just only a linear output layer must be taught. In this paper a reservoir is proposed to be built using neo-fuzzy neurons which means that Reservoir Computing and paradigms and fuzzy logic are combined.

Keywords: reservoir computing, hybrid systems, neo-fuzzy neuron, online learning procedure, prediction.

ACM Classification Keywords: I.2.6 Learning – Connectionism and neural nets.

Link:

RESERVOIR FORECASTING NEURO-FUZZY NETWORK AND ITS LEARNING

Yevgeniy Bodyanskiy, Oleksii Tyshchenko, Iryna Pliss

http://www.foibg.com/ijita/vol20/ijita20-03-p01.pdf