Training Neurofuzzy Networks with Participatory Learning

This paper introduces a new approach to adjust a class of neurofuzzy networks based on the idea of participatory learning. Participatory learning is a mean to learn and revise beliefs based on what is already known or believed. The performance of the approach is verified with the Box and Jenkins gas furnace modeling problem, and with a shortterm load forecasting problem using actual data. Comparisons with alternative training procedures suggested in the literature are included to shown the effectiveness of participatory learning to train neurofuzzy networks.

• Type: Conference
• Year: 2007
• Where: EUSFLAT
• Authors: Michel Hell, Rosangela Ballini, Pyramo Costa Jr., Fernando A. C. Gomide
• Keywords: EUSFLAT 2007, Furnace Modeling Problem, Neurofuzzy Networks, Participatory Learning