We propose a general framework for increasing local stability of Artificial Neural Nets (ANNs) using Robust Optimization (RO). We achieve this through an alternating minimization-maximization procedure, in which the loss of the network is minimized over perturbed examples that are generated at each parameter update. We show that adversarial training of ANNs is in fact robustification of the net...

Due to remarkable capabilities of artificial neural networks (ANNs) such as generalization and nonlinear system modeling, ANNs have been extensively studied and applied in a wide variety of applications (Amiri et al., 2007; Davande et al., 2008). The rapid development of ANN technology in recent years has led to an entirely new approach for the solution of many data processing-based problems, u...

Artificial neural networks (ANNs) and Bayesian belief networks (BBNs) utilizing select environmental variables were developed and evaluated, with the intent to model net ecosystem metabolism (a proxy for system trophic state) within a freshwater wetland. Network modeling was completed independently for distinct data subsets, representing periods of ‘low’ and ‘high’ water levels throughout in th...

In medicine at present, neural networks are a ‘hot’ research area, particularly in cardiology, radiology, urology, oncology etc. In the area of computer science, this new technology has been accepted. The purpose of a neural network is to map an input into a desired output. Combining neurons into layers permits artificial neural networks to solve highly complex classification problems. The vari...

Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. ANNs are one of the three main components of computational intelligence and, as such, they have been often hybridized from different perspectives. In this paper, a review of some of the main contributions for hybrid ANNs is given, considering three points of views: mode...

During recent decades, recognizing letters was a considerable discussion for artificial intelligence researchers and recognize letters due to the variety of languages and different approaches have many challenges. The Artificial Neural Networks (ANNs) are framed based on particular application such as recognition pattern and data classification through learning process is configured. So, it is ...

estimating the final price of products is of great importance. for manufacturing companies proposing a final price is only possible after the design process over. these companies propose an approximate initial price of the required products to the customers for which some of time and money is required. here using the existing data of already designed transformers and utilizing the bayesian anal...

Artificial Neural Networks (ANNs), especially back-propagation (BP) neural network, can improve the performance of intrusion detection systems. However, for the current network intrusion detection methods, the detection precision, especially for lowfrequent attacks, detection stability and training time are still needed to be enhanced. In this paper, a new model which based on optimized BP neur...

in this paper, the artificial neural network (ann) approach is applied for forecasting groundwater level fluctuation in aghili plain,southwest iran. an optimal design is completed for the two hidden layers with four different algorithms: gradient descent withmomentum (gdm), levenberg marquardt (lm), resilient back propagation (rp), and scaled conjugate gradient (scg). rain,evaporation, relative...

in this paper, the artificial neural network (ann) approach is applied for forecasting groundwater level fluctuation in aghili plain,southwest iran. an optimal design is completed for the two hidden layers with four different algorithms: gradient descent withmomentum (gdm), levenberg marquardt (lm), resilient back propagation (rp), and scaled conjugate gradient (scg). rain,evaporation, relative...