Backpropagation Networks Modelling: Appropriate Structure and Convergence Speed
نویسندگان
چکیده
The Bayesian Information Criterion (BIC) was presented to obtain the appropriate structure, via the number of hidden nodes, and a new algorithm was proposed to improve the convergence speed of backpropagation training method. The algorithm was obtained by employing the conjugate gradient method to solve the nonlinear part in the weights of the hidden layers and the Kalman filter to solve the linear part in the weights of the output layer. From simulation experiments with quarterly economic data on the exports and gross domestic product (GDP) in Thailand, it was found that the BIC and the algorithm could perform satisfactorily. Key-words:Backpropagation networks, Bayesian information criterion, Conjugate gradient method, Kalman filter
منابع مشابه
Fuzzy Neural Network Modelling for Tool Wear Estimation in Dry Milling Operation
Tool failure may result in losses in surface finish and dimensional accuracy of a finished part, or possible damage to the work piece and machine. This paper presents a Fuzzy Neural Network (FNN) which is designed and developed for machinery prognostic monitoring. The FNN is basically a multi-layered fuzzy-rule-based neural network which integrates a fuzzy logic inference into a neural network ...
متن کاملTransfer of learning in backpropagation and in related neural network models
Given the range of neural network paradigms available at the moment, we might ask why anyone would still want to use backpropagation. An important argument for using this learning algorithm seems to be its popularity. Backpropagation has become one of the standard technologies in connectionist modelling. Although it was invented by Werbos in 1974, it has only been with the publication of the so...
متن کاملA Fuzzy Neural Network and Its Matlab Simulation
A fuzzy neural network and its relevant fuzzy neuron and fuzzy learning algorithm are introduced. An object-oriented implementation of fuzzy neural network in MATLAB environment is realized. Simulations are carried out by SIMULINK. The performance of fuzzy neural network is experimentally compared with other neural networks trained by backpropagation algorithms. It shows better convergence spee...
متن کاملA Variant of Back-propagation Algorithm for Multilayer Feed-forward Network
In this paper, a variant of Backpropagation algorithm is proposed for feed-forward neural networks learning. The proposed algorithm improve the backpropagation training in terms of quick convergence of the solution depending on the slope of the error graph and increase the speed of convergence of the system. Simulations are conducted to compare and evaluate the convergence behavior and the spee...
متن کاملNew Learning Automata Based Algorithms for Adaptation of Backpropagation Algorithm Parameters
One popular learning algorithm for feedforward neural networks is the backpropagation (BP) algorithm which includes parameters, learning rate (eta), momentum factor (alpha) and steepness parameter (lambda). The appropriate selections of these parameters have large effects on the convergence of the algorithm. Many techniques that adaptively adjust these parameters have been developed to increase...
متن کامل