Fuzzy parameter adaptation in optimization: some neural net training examples
Payman Arabshahi, J.J. Choi, Robert J. Marks, Thomas P. Caudell · IEEE Computational Science and Engineering · 1996
Parameters of certain neural net training algorithms and classification procedures are often chosen or adapted using heuristics that contain fuzzy descriptors. Such heuristics, quantified into a fuzzy inference engine, can take the human out of the loop and provide for faster convergence or improved performance. Other applications, outside of neural nets, are also possible.