This paper discusses the notion of generalization of training samples over long distances in the input space of a feedforward neural network. Such a generalization might occur in various ways, that di er in how great the contribution of di erent training features should be. The structure of a neuron in a feedforward neural network is analyzed and it is concluded, that the actual performance of ...

In this paper, we propose a novel recursive recurrent neural network (R2NN) to model the end-to-end decoding process for statistical machine translation. R2NN is a combination of recursive neural network and recurrent neural network, and in turn integrates their respective capabilities: (1) new information can be used to generate the next hidden state, like recurrent neural networks, so that la...

This paper presents the application of three main Artificial Neural Networks (ANNs) in damage detection of steel bridges. This method has the ability to indicate damage in structural elements due to a localized change of stiffness called damage zone. The changes in structural response is used to identify the states of structural damage. To circumvent the difficulty arising from the non-linear n...

In order to protect valuable computer systems, network data needs to be analyzed and classified so that possible network intrusions can be detected. Machine learning techniques have been used to classify network data. For supervised machine learning methods, they can achieve high accuracy at classifying network data as normal or malicious, but they require the availability of fully labeled data...

in this paper, we introduce a hybrid approach based on neural network and optimization teqnique to solve ordinary differential equation. in proposed model we use heyperbolic secont transformation function in hiden layer of neural network part and bfgs teqnique in optimization part. in comparison with existing similar neural networks proposed model provides solutions with high accuracy. numerica...

In this study, two kinds of neural networks are employed to develop a supervised ECG beat classifier. In order to improve the performance of the MLP classifier for application to ECG signal, the performance is compared to an LVQ neural network classifier. The two classifiers are tested with selected ECG time series and experimental results show that the MLP classifier offers a great potential i...

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...

In Machine learning and artificial intelligence have seemingly never been as typical and relevant to real-time applications as they are in these days autonomous, big data era. The fortune of machine learning and artificial intelligence depends on the coexistence of three important conditions: powerful computing environments, rich and/or large data, and efficient learning techniques (algorithms)...

today, with the advanced statistical techniques and neural networks, predictive models of distribution have been rapidly developed in ecology. purpose of this research is to predict and map the distribution of tetranychus urticae koch (acari: tetranychidae) using mlp neural networks combined with genetic algorithm in surface of farm. population data of pest was obtained in 2016 by sampling in 1...

this paper extends the sequential learning algorithm strategy of two different types of adaptive radial basis function-based (rbf) neural networks, i.e. growing and pruning radial basis function (gap-rbf) and minimal resource allocation network (mran) to cater for on-line identification of non-linear systems. the original sequential learning algorithm is based on the repetitive utilization of s...