S. C. Lee and E. T. Lee, "Fuzzy Neural Networks", Mathematical Biosciences, vol. 23, 1975, pp. 151-177.  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... 1111 1111 1111 max point min point Class 1 Class 2 Figure 12: Fuzzy hyperboxes Several models combining fuzzy systems and neural networks have been developed that build efficient pattern classifiers exploiting the particular advantages offered by each technique in a synergistic manner [8, 12, 24, 69, 91, 101]. Most of these methods use the training set to produce geometrical hyperboxes and then compute suitable membership functions in order to specify the desicion boundaries of pattern classes (Fig. 12) In the next sections four such structures are described that may be viewed as representative ....

S. Lee and E. Lee. Fuzzy Neural Networks. Math. Biosciences, 23:151--177, 1975.

....approaches has produced multiple and diverse works in recent years. This paper proposes an approach to a taxonomy of fuzzy neural system according to their symbolic and connectionist components, and their application. 1 Introduction The concept of fuzzy neural networks was created two decades ago [1] but the recent resurgence with a great amount of published works may be motivated by the increasing recognition of the potential of fuzzy logic and neural networks in different areas of theoretical and applied research. At this moment, many researchers are investigating ways to build fuzzy neural ....

S.C Lee and E.T. Lee. Fuzzy neural networks. Mathematical Biosciences, 23:151--177, 1975.

....digital circuit design [10] and in the design of intelligent human computer interfaces [14] The fundamentals of FFAs have been in discussed in [13] without presenting a systematic method for machine synthesis. Neural network implementations of fuzzy automata have been proposed in the literature [8, 9, 18]. A general synthesis method for synchronous fuzzy sequential circuits has been discussed in [20] A synthesis method for a class of discrete time neural networks with multilevel threshold neurons with applications to gray level image processing has been proposed in [15] Published in ....

S. Lee and E. Lee, "Fuzzy neural networks," Mathematical Biosciences, vol. 23, pp. 151--177, 1975.

....algorithm for classification of input patterns. In the Third Chapter we explain the basic principles of fuzzy neural hybrid systems. In the Fourth Chapter we present some excercises for the Reader. Chapter 1 Fuzzy Systems 1. 1 An introduction to fuzzy logic Fuzzy sets were introduced by Zadeh [113] as a means of representing and manipulating data that was not precise, but rather fuzzy. There is a strong relationship between Boolean logic and the concept of a subset, there is a similar strong relationship between fuzzy logic and fuzzy subset theory. In classical set theory, a subset A of a ....

.... x is in A is true is determined by finding the ordered pair (x, A (x) The degree of truth of the statement is the second element of the ordered pair. It should be noted that the terms membership function and fuzzy subset get used interchangeably. 2 1 1 2 3 1 4 0 Definition 1.1. 1 [113] Let X be a nonempty set. A fuzzy set A in X is characterized by its membership function A : X # [0, 1] and A (x) is interpreted as the degree of membership of element x in fuzzy set A for each x # X. It is clear that A is completely determined by the set of tuples A = x, A (x) x ....

[Article contains additional citation context not shown here]

S.C. Lee and E.T. Lee, Fuzzy neural networks, Math. Biosci. 23(1975) 151-177.

....circuit design [27] and in the design of intelligent human computer interfaces [41] The fundamentals of FFAs have been in discussed in [14, 40, 54] without presenting a systematic method for machine synthesis. Neural network implementations of fuzzy automata have been proposed in the literature [18, 19, 25, 49]. The synthesis method proposed in [18] uses digital design technology to implement fuzzy representations of states and outputs. In [49] the implementation of a Moore machine with fuzzy inputs and states is realized by training a feedforward network explicitly on the state transition table using ....

S. Lee and E. Lee, "Fuzzy neural networks," Mathematical Biosciences, vol. 23, pp. 151--177, 1975.

....circuit design [36] and in the design of intelligent human computer interfaces [51] The fundamentals of FFAs have been in discussed in [17, 50, 66] without presenting a systematic method for machine synthesis. Neural network implementations of fuzzy automata have been proposed in the literature [21, 22, 30, 61]. The synthesis method proposed in [21] uses digital design technology to implement fuzzy representations of states and outputs. In [61] the implementation of a Moore machine with fuzzy inputs and states is realized by training a feedforward network explicitly on the state transition table using ....

S. Lee and E. Lee, "Fuzzy neural networks," Mathematical Biosciences, vol. 23, pp. 151--177, 1975.

....each fuzzy rule is realized using a neural network, when the fuzzy inference is the result of several neural networks [56] The former subgroup is studied in more detail in this thesis. In the fuzzy neural networks [15, 49, 50] the fuzzy ideas are incorporated into neural networks. Lee and Lee [37] are the first who worked on neuro fuzzy systems, especially on fuzzy neural networks. Their approach replaced the weighted sum of the McCulloch Pitts neuron by an corresponding fuzzy operation. The operation of their neuro fuzzy system was exactly the same as the McCulloch Pitts neural network. ....

S. C. Lee and E. T. Lee, "Fuzzy neural networks," Mathematical Biosciences, vol. 23, pp. 151--177, 1975.

No context found.

S. C. Lee and E. T. Lee, "Fuzzy Neural Networks", Mathematical Biosciences, vol. 23, 1975, pp. 151-177.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC