The Petri Net Radial Basis Function Perceptron
نویسنده
چکیده
This paper introduces the Petri Net Radial Basis Function Perceptron (PNRBFP), a modified Petri Net that exhibits behavior equivalent to that of a typical radial basis function Perceptron when used in neural networking applications under certain domain restrictions. The PNRBFP makes use of modified transitions to perform basis function calculations and 'fuzzy' style tokens to transport values of basis function outputs. In all other respects the PNRBFP is a standard Petri Net and will benefit from established Petri Net analysis and implementation tools.
منابع مشابه
Implementation of a Neural Network Using Simulator and Petri Nets
This paper describes construction of multilayer perceptron by open source neural networks simulator Neuroph and Petri net. The described multilayer perceptron solves logical function "xor "exclusive or. The aim is to explore the possibilities of description of the neural networks by Petri Nets. The selected neural network (multilayer perceptron) allows to be seen clearly the advantages and disa...
متن کاملMultilayer Perceptron, Radial Basis Function Network, and Self–organizing Map in the Problem of Face Recognition
In this contribution, one and two-stage neural networks methods for face recognition are presented. For two-stage systems, the Kohonen self-organizing map is used as a feature extractor and multiplayer perceptron (MLP) or radial basis function (RBF) network are used as classifiers. The results of such recognition are compared with face recognition using a one-stage multilayer perceptron and rad...
متن کاملRBF Nets in Faults Localization
The task of faults localization is discussed in a model-free setting. As a tool for its solution we consider a multiclass pattern recognition problem with a metric in the label space. Then, this problem is approximately solved, providing hints on selecting appropriate RBF nets. It was shown that the approximate solution is the exact one in several important cases. Finally, we propose the algori...
متن کاملComparing the Performance of Mathematical Models for Surgical Decisions on Head Injury Patients
This paper compares three mathematical models for surgical decisions on head injury patients. A logistic regression and two neural network models were developed using a large clinical database. Using randomly selected 9480 cases as the training group and another 3160 cases as the validation group. We evaluated the performance of a logistic regression model, a multi-layer perceptron (MLP) neural...
متن کاملLearning Heterogeneous Functions from Sparse and Non-Uniform Sample
A boosting-based method for centers placement in radial basis function networks (RBFN) is proposed. Also, the influence of several methods for drawing random samples on the accuracy of RBFN is examined. The new method is compared to trivial, linear and non-linear regressors including the multilayer Perceptron and alternative RBFN learning algorithms and its advantages are demonstrated for learn...
متن کامل