Let m be the number of time-varying variables for storing temporal events in a fully recurrent sequence processing network. Let R time be the ratio between the number of operations per time step (for an exact gradient based supervised sequence learning algorithm), and m. Let R space be the ratio between the maximum number of storage cells necessary for learning arbitrary sequences, and m. With ...

The paper deals with a discrete-time recurrent neural network designed with dynamic neuron models. Dynamics are reproduced within each single neuron, hence the considered network is a locally recurrent globally feedforward. In the paper, conditions for global stability of the neural network considered are derived using the Lyapunov’s second method.

Recurrent Neural Networks were invented a long time ago, and dozens of different architectures have been published. In this paper we generalize recurrent architectures to a state space model, and we also generalize the numbers the network can process to the complex domain. We show how to train the recurrent network in the complex valued case, and we present the theorems and procedures to make t...

Due to the multi-variable, nonlinear, large time delay and strong coupling features of the wastewater treatment process, a recurrent high-order neural network is used to model the key water quality parameters(Chemical Oxygen Demand, Biological Oxygen Demand, Suspended Solid and Ammonia Nitrogen) for the wastewater treatment process, and the neural network is trained by an filtering algorithm. O...

This paper presents methods for estimating time delay margin for adaptive control of input delay systems with almost linear structured uncertainty and a step input reference command signal. The bounded linear stability analysis method seeks to represent an adaptive law by a locally bounded linear approximation within a time window. The time delay margin of this input delay system represents a l...

An oral sustained-release floating tablet formulation of metformin HCl was designed and developed. Effervescence and swelling properties were attributed on the developed tablets by sodium bicarbonate and HPMC-PEO polymer combination, respectively. Tablet composition was optimized by response surface methodology (RSM). Seventeen (17) trial formulations were analyzed according to Box-Behnken desi...

The real macroeconomic instability and frequent changes in the monetary and banking regulations with financial contagion to the banks’ financial statements in the banking network of Iran cause intensified instabilities in its financial behaviors. In this paper, using statistical analysis and three-dimensional charts, we have analyzed the behavior of the financial statements of consolidated bala...

Learning long-term temporal dependencies with recurrent neural networks can be a difficult problem. It has recently been shown that a class of recurrent neural networks called NARX networks perform much better than conventional recurrent neural networks for learning certain simple long-term dependency problems. The intuitive explanation for this behavior is that the output memories of a NARX ne...

Learning long-term temporal dependencies with recurrent neural networks can be a difficult problem. It has recently been shown that a class of recurrent neural networks called NARX networks perform much better than conventional recurrent neural networks for learning certain simple long-term dependency problems. The intuitive explanation for this behavior is that the output memories of a NARX ne...