A fast learning algorithm for evolving neo-fuzzy neuron

• Evolving algorithm for a neo-fuzzy network modeling approach is developed.
• The parameters of the network are updated using a scheme with optimal learning rate.
• The structure of the model evolves through the inclusion/exclusion of fuzzy rules.
• The approach is fast, accurate, and computationally efficient.

This paper introduces an evolving neural fuzzy modeling approach constructed upon the neo-fuzzy neuron and network. The approach uses an incremental learning scheme to simultaneously granulate the input space and update the neural network weights. The neural network structure and parameters evolve simultaneously as data are input. Initially the space of each input variable is granulated using two complementary triangular membership functions. New triangular membership functions may be added, excluded and/or have their parameters adjusted depending on the input data and modeling error. The parameters of the network are updated using a gradient-based scheme with optimal learning rate. The performance of the approach is evaluated using instances of times series forecasting and nonlinear system identification problems. Computational experiments and comparisons against alternative evolving models show that the evolving neural neo-fuzzy network is accurate and fast, characteristics which are essential for adaptive systems modeling, especially in real-time, on-line environments.

Figure optionsDownload as PowerPoint slide