This research investigates the analysis and efficiency of neural networks, using a technique for network link pruning. The technique is tested with inefficient architectures for the XOR problem and then for a network from a real world, complex, image recognition task. By removing each link and examining effect upon error level, a fuzzy set is developed with membership indicating link saliency. ...

This article, by leaving pre-determined membership function of a fuzzy set which is a basic assumption for such subject, will try to propose a hybrid technique to select the most economic project among alternative projects in fuzziness interest rates condition. In this way, net present worth (NPW) would be the economic indicator. This article tries to challenge the assumption of large sample si...

interval-valued intuitionistic fuzzy sets (ivifss) are widely used to handle uncertainty and imprecision in decision making. however, in more complicated environment, it is difficult to express the uncertain information by an ivifs with considering the decision-making preference. hence, this paper proposes a group generalized interval-valued intuitionistic fuzzy soft set (g-givifss) which conta...

investigation of reliability characteristics under fuzzy environments is proposed in this paper. fuzzy weibull distribution and lifetimes of components are using it described. formulas of a fuzzy reliability function, fuzzy hazard function and their α-cut set are presented. furthermore, the fuzzy functions of series systems and parallel systems are discussed, respectively. finally, some numeric...

The investigation of impact of fuzzy sets on zero forcing set is the main aim of this paper. According to this, results lead us to a new concept which we introduce it as Fuzzy Zero Forcing Set (FZFS). We propose this concept and suggest a polynomial time algorithm to construct FZFS. Further more we compute the propagation time of FZFS on fuzzy graphs. This concept can be more efficient to model...

in this paper, we use parametric form of fuzzy number and we converta fuzzy linear system to two linear system in crisp case. conditions for the existence of a minimal solution to $mtimes n$ fuzzy linear equation systems are derived and a numerical procedure for calculating the minimal solution is designed. numerical examples are presented to illustrate the proposed method.