Output details
13 - Electrical and Electronic Engineering, Metallurgy and Materials
Queen's University Belfast
A New Gradient Descent Approach for Local Learning of Fuzzy Neural Models
The majority of reported learning methods for Takagi-Sugeno-Kang(TSK) fuzzy neural models to date mainly focus on the improvement of model accuracy. How to find a desirable set of fuzzy partitions and, hence, identify the corresponding consequent models which can be directly explained in terms of system local behaviour, presents a critical step in fuzzy neural modelling. This EPSRC-funded work led to a new integrated gradient descent learning and the method is further supported by 2013 EPSRC project (EP/L001063/1) for developing new EV charging system, and also in the 2013 InvestNI Proof of Concept project Fuzzy controller for polymer extrusion.