Approximation Properties of the Neuro-Fuzzy Minimum Function
Andreas Gottschling, Christof Kreuter · Contributions to management science · 2000
The integration of fuzzy logic systems and neural networks in data driven nonlinear modeling applications has generally been limited to functions based upon the multiplicative fuzzy implication rule for theoretical and computational reasons. We derive a universal approximation result for the minimum fuzzy implication rule as well as a differentiable substitute function that allows fast optimization and function approximation with neuro-fuzzy networks.