A Particle Swarm Optimization Approach for Training Artificial Neural Networks with Uncertain Data
نویسندگان
چکیده
Abstract. Artificial neural networks are powerful tools to learn functional relationships between data. They are widely used in engineering applications. Recurrent neural networks for fuzzy data have been introduced to map uncertain structural processes with deterministic or uncertain network parameters. Based on swarm intelligence, a new training strategy for neural networks is presented in this paper. Accounting for uncertainty in measurements, particle swarm optimization (PSO) approaches using interval and fuzzy numbers are developed. Applications are focused on the description of time-dependent material behavior with recurrent neural networks for uncertain data within interval and fuzzy finite element analyses. Network training with PSO allows to create special network structures with dependent parameters in order to consider physical boundary conditions of investigated materials.
منابع مشابه
Traffic Signal Prediction Using Elman Neural Network and Particle Swarm Optimization
Prediction of traffic is very crucial for its management. Because of human involvement in the generation of this phenomenon, traffic signal is normally accompanied by noise and high levels of non-stationarity. Therefore, traffic signal prediction as one of the important subjects of study has attracted researchers’ interests. In this study, a combinatorial approach is proposed for traffic signal...
متن کاملArtificial Intelligence Based Approach for Identification of Current Transformer Saturation from Faults in Power Transformers
Protection systems have vital role in network reliability in short circuit mode and proper operating for relays. Current transformer often in transient and saturation under short circuit mode causes mal-operation of relays which will have undesirable effects. Therefore, proper and quick identification of Current transformer saturation is so important. In this paper, an Artificial Neural Network...
متن کاملComparative Analysis of Neural Network Training Methods in Real-time Radiotherapy
Background: The motions of body and tumor in some regions such as chest during radiotherapy treatments are one of the major concerns protecting normal tissues against high doses. By using real-time radiotherapy technique, it is possible to increase the accuracy of delivered dose to the tumor region by means of tracing markers on the body of patients.Objective: This study evaluates the accuracy ...
متن کاملUsing Particle Swarm Optimization to Pre-Train Artificial Neural Networks: Selecting Initial Training Weights for Feed-Forward Back-Propagation Neural Networks
Performance 1 of supervised training of Artificial Neural Networks (ANNs) depends on several factors, including neural network architecture, number of neurons in hidden layers, the neurons' activation functions, and selection of initial network parameters (connection weights). Trial and error is commonly used to select the network parameters and the initial connection weights. Such practice can...
متن کاملNeuro-Optimizer: A New Artificial Intelligent Optimization Tool and Its Application for Robot Optimal Controller Design
The main objective of this paper is to introduce a new intelligent optimization technique that uses a predictioncorrectionstrategy supported by a recurrent neural network for finding a near optimal solution of a givenobjective function. Recently there have been attempts for using artificial neural networks (ANNs) in optimizationproblems and some types of ANNs such as Hopfield network and Boltzm...
متن کامل