Yazar "Bittermann, Michael S." seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Yayın
    A fuzzy neural tree based on likelihood
    (Institute of Electrical and Electronics Engineers Inc., 2015) Çiftçioğlu, Özer; Bittermann, Michael S.
    A novel type of fuzzy neural system is presented. It involves the neural tree concept and is termed as fuzzy neural tree (FNT). Each tree node uses a Gaussian as a fuzzy membership function so that the approach uniquely is in align with both the probabilistic and possibilistic interpretations of fuzzy membership, thereby presenting a novel type of network. The tree is structured by the domain knowledge and parameterized by likelihood. The FNT is described in detail pointing out its various potential utilizations, in which complex modeling and multi-objective optimization are demanded. One of such utilizations concerns design. This is exemplified and its effectiveness is demonstrated by computer experiments in the realm of Architectural design. © 2015 IEEE.
  • Küçük Resim Yok
    Yayın
    Precision constrained optimization by exponential ranking
    (Institute of Electrical and Electronics Engineers Inc., 2016) Bittermann, Michael S.; Çiftçioğlu, Özer
    Demonstrative results of a probabilistic constraint handling approach that is exclusively using evolutionary computation are presented. In contrast to other works involving the same probabilistic considerations, in this study local search has been omitted, in order to assess the necessity of this deterministic local search procedure in connection with the evolutionary one. The precision stems from the non-linear probabilistic distance measure that maintains stable evolutionary selection pressure towards the feasible region throughout the search, up to micro level in the range of 10 -10 or beyond. The details of the theory are revealed in another paper [1]. In this paper the implementation results are presented, where the non-linear distance measure is used in the ranking of the solutions for effective tournament selection. The test problems used are selected from the existing literature. The evolutionary implementation without local search turns out to be already competitively accurate with sophisticated and accurate state-of-the-art constrained optimization algorithms. This indicates the potential for enhancement of the sophisticated algorithms, as to their precision and accuracy, by the integration of the proposed approach. © 2016 IEEE.