Evolving Weights and Transfer Functions in Feed Forward Neural Networks
نویسندگان
چکیده
In this paper we show different evolutionary algorithms applied to the simultaneous off-line evolution of weights and transfer functions of feed-forward neural networks. Experimentation has been carried out with classical benchmarks when weights and both weights and transfer function are evolved and a comparison of the proposed evolutionary methods with classical methodologies (the back-propagation algorithm) are shown. Results are very promising and show the effectiveness of the addressed evolutionary methodologies to solve the problem of simultaneously finding the optimal weights and transfer functions of a neural network.
منابع مشابه
Prediction of the Liquid Vapor Pressure Using the Artificial Neural Network-Group Contribution Method
In this paper, vapor pressure for pure compounds is estimated using the Artificial Neural Networks and a simple Group Contribution Method (ANN–GCM). For model comprehensiveness, materials were chosen from various families. Most of materials are from 12 families. Vapor pressure data of 100 compounds is used to train, validate and test the ANN-GCM model. Va...
متن کاملTraining Feed-Forward Neural Networks Using Firefly Algorithm
In this work, firefly algorithm (FA) is used in training feed-forward neural networks (FNN) for classification purpose. In experiments, three well-known classification problems have been used to evaluate the performance of the proposed FA. The experimental results obtained by FA were compared with the results reported by artificial bee colony (ABC) algorithm and genetic algorithm (GA). Also, si...
متن کاملNumerical treatment for nonlinear steady flow of a third grade fluid in a porous half space by neural networks optimized
In this paper, steady flow of a third-grade fluid in a porous half space has been considered. This problem is a nonlinear two-point boundary value problem (BVP) on semi-infinite interval. The solution for this problem is given by a numerical method based on the feed-forward artificial neural network model using radial basis activation functions trained with an interior point method. ...
متن کاملSTRUCTURAL DAMAGE DETECTION BY MODEL UPDATING METHOD BASED ON CASCADE FEED-FORWARD NEURAL NETWORK AS AN EFFICIENT APPROXIMATION MECHANISM
Vibration based techniques of structural damage detection using model updating method, are computationally expensive for large-scale structures. In this study, after locating precisely the eventual damage of a structure using modal strain energy based index (MSEBI), To efficiently reduce the computational cost of model updating during the optimization process of damage severity detection, the M...
متن کاملSolving nonlinear Lane-Emden type equations with unsupervised combined artificial neural networks
In this paper we propose a method for solving some well-known classes of Lane-Emden type equations which are nonlinear ordinary differential equations on the semi-innite domain. The proposed approach is based on an Unsupervised Combined Articial Neural Networks (UCANN) method. Firstly, The trial solutions of the differential equations are written in the form of feed-forward neural networks cont...
متن کامل