the probability of losing a customer in m/g/n/0 and gi/m/n/0 loss queuing systems withheterogeneous servers is minimized. the first system uses a queue discipline in which a customer who arriveswhen there are free servers chooses any one of them with equal probability, but is lost otherwise. providedthat the sum of the servers rates are fixed, loss probability in this system attains minimum val...

modelling and forecasting stock market is a challenging task for economists and engineers since it has a dynamic structure and nonlinear characteristic. this nonlinearity affects the efficiency of the price characteristics. using an artificial neural network (ann) is a proper way to model this nonlinearity and it has been used successfully in one-step-ahead and multi-step-ahead prediction of di...

Modelling and forecasting Stock market is a challenging task for economists and engineers since it has a dynamic structure and nonlinear characteristic. This nonlinearity affects the efficiency of the price characteristics. Using an Artificial Neural Network (ANN) is a proper way to model this nonlinearity and it has been used successfully in one-step-ahead and multi-step-ahead prediction of di...

i Foreword Recurrent neural networks are an attractive tool for both practical applications and for the modeling of biological nerve nets, but their successful application requires an understanding of their dynamical properties, in particular, their stability. The present work provides an in-depth study of this challenging issue and contributes a number of new results that are also important fo...

We present a frequency domain analysis of additive recurrent neural networks based on the pas-sivity approach to input-output stability. We apply graphical Circle Criteria for the case of normal weight matrices which result in eeectively computable stability bounds, including systems with delay. Approximation techniques yield further gen-eralisation to arbitrary matrices.

We present a novel approach to unsupervised temporal sequence processing in the form of an unsupervised, recurrent neural network based on a selforganizing map (SOM). A standard SOM clusters each input vector irrespective of context, whereas the recurrent SOM presented here clusters each input based on an input vector and a context vector. The latter acts as a recurrent conduit feeding back a 2...

Attention distributions of the generated translations are a useful bi-product of attention-based recurrent neural network translation models and can be treated as soft alignments between the input and output tokens. In this work, we use attention distributions as a confidence metric for output translations. We present two strategies of using the attention distributions: filtering out bad transl...