Robustness of deep neural networks is a critical issue in practical applications. In the general case feed-forward (including convolutional network architectures), under random noise attacks, we propose to study probability that output deviates from its nominal value by given threshold. We derive simple concentration inequality for propagation input uncertainty through using Cramer–Chernoff met...

This work addresses an efficient neural network (NN) representation for the phase-field modeling of isotropic brittle fracture. In recent years, data-driven approaches, such as networks, have become active research field in mechanics. this contribution, deep networks—in particular, feed-forward (FFNN)—are utilized directly development failure model. The verification and generalization trained m...

In this study, the method to apply the feed forward neural networks with two different numbers of hidden layers for harmonic detection process in active filter are described. We have simulated the distorted wave including 5th, 7th, 11th, 13th harmonics and used them for training of the neural networks. The distorted wave including up to 25th harmonics were prepared for testing of the neural net...

Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same problem. More specifically, feed-forward artificial neural networks are trained with three different back propagation algorithms, ...

The paper presents the possibility of the design of frontal neural networks and feed-forward neural networks (without pre-processing of inputs time series) with learning algorithms on the basis genetic and eugenic algorithms and Takagi-Sugeno fuzzy inference system (with pre-processing of inputs time series) in predicting of gross domestic product development by designing a prediction models wh...

This paper proposed a chemical substance detection method using the Long Short-Term Memory of Recurrent Neural Networks (LSTM-RNN). The chemical substance data was collected using a mass spectrometer which is a time-series data. The classification accuracy using the LSTM-RNN classifier is 96.84%, which is higher than 75.07% of the ordinary feed forward neural networks. The experimental results ...

this paper proposes a method for the prediction of pore size values in hydrocarbon reservoirs using 3d seismic data. to this end, an actual carbonate oil field in the south-western part ofiranwas selected. taking real geological conditions into account, different models of reservoir were constructed for a range of viable pore size values.  seismic surveying was performed next on these models. f...