Deineko A. Adaptive learning of evolutionary neuro-fuzzy systems with kernel activation functions in data mining tasks

The thesis is devoted to the development of evolving neural networks and neuro-fuzzy systems with kernel activation function that contain fuzzy support vector machine, radial basis function neural network and general regression neuro-fuzzy network as subsystems is proposed. This network is tuned using both optimization and memory based approaches and does not suffer from the "curse of dimensionality", is able to real time mode information processing by adapting its parameters and structure to problem conditions. The evolving architecture and adaptive method of learning neuro-fuzzy system that adjusts not only their synaptic weights, but also automatically determines the quantity of neurons, the location of centers of membership functions and parameters of the receptive fields in on-line mode with high speed and operation-data was proposed.