Incorporating Fuzzy Membership Functions into Evolutionary Probabilistic Neural Networks
نویسندگان
چکیده
In this contribution a new supervised classification model is proposed, namely the Fuzzy Evolutionary Probabilistic Neural Network (FEPNN). The proposed model incorporates a fuzzy class membership function into the recently proposed Evolutionary Probabilistic Neural Network (EPNN). EPNN employs an evolutionary algorithm, namely the Particle Swarm Optimization (PSO), for the selection of the spread parameters and prior probabilities of Probabilistic Neural Networks. FEPNN combines efficient and effective evolutionary algorithms as well as techniques from fuzzy set theory. This combination provides an adequate model that achieves similar and superior performance than the well known and widely used Feed Forward Neural Networks (FNNs). FEPNN is applied to a credit card approval task with promising results.
منابع مشابه
Novel Radial Basis Function Neural Networks based on Probabilistic Evolutionary and Gaussian Mixture Model for Satellites Optimum Selection
In this study, two novel learning algorithms have been applied on Radial Basis Function Neural Network (RBFNN) to approximate the functions with high non-linear order. The Probabilistic Evolutionary (PE) and Gaussian Mixture Model (GMM) techniques are proposed to significantly minimize the error functions. The main idea is concerning the various strategies to optimize the procedure of Gradient ...
متن کاملFuzzy Evolutionary Probabilistic Neural Networks
One of the most frequently used models for classification tasks is the Probabilistic Neural Network. Several improvements of the Probabilistic Neural Network have been proposed such as the Evolutionary Probabilistic Neural Network that employs the Particle Swarm Optimization stochastic algorithm for the proper selection of its spread (smoothing) parameters and the prior probabilities. To furthe...
متن کاملEvolutionary - Based Learning Applied to Fuzzy Controllers . Luis Magdalena , F elix
|Fuzzy Logic Controllers constitute knowledge-based systems that include fuzzy rules and fuzzy membership functions to incorporate the human knowledge into their knowledge base. The deenition of fuzzy rules and fuzzy membership functions is actually aaected by subjective decisions, having a great innuence over the whole FLC performance. Some eeorts have been made to obtain an improvement on sys...
متن کاملFuzzy characterization of Kernel-based neural Networks
In Neural Networks models the knowledge synthesized from the training process is represented in a subsymbolic fashion (weights, kernels, combination of numerical descriptions) that makes difficult its interpretation. The interpretation of the internal representation of a successful Neural Network can be useful to understand the nature of the problem and its solution, to use the Neural "model" a...
متن کاملTheory and Design of a Hybrid Pattern Recognition System
Pattern recognition methods can be divided into four di erent categories: statistical or probabilistic, structural, possibilistic or fuzzy, and neural methods. A formal analysis shows that there is a computational complexity versus representational power trade-o between probabilistic and possibilistic or fuzzy set measures, in general. Furthermore, sigmoidal theory shows that fuzzy set membersh...
متن کامل