Regularized fuzzy neural networks based on nullneurons for problems of classification of patterns

This paper presents a learning algorithm for fuzzy neural networks based on nullneurons able to generate accurate and transparent models. The learning algorithm is based on ideas from Extreme Learning Machine, to achieve a low time complexity, and regularization method, resulting in sparse and accurate models. Experiments considering pattern classification are detailed. Results suggest the proposed approach as a promising alternative for pattern recognition with a good accuracy and some level of interpretability.