An improved universal parallel recurrent neural network canonical architecture, named Recurrent Trainable Neural Network (RTNN), suited for state-space systems identification, and an improved dynamic back-propagation method of its learning, are proposed. The proposed RTNN is studied with various representative examples and the results of its learning are compared with other results,, given in t...

An improved universal parallel recurrent neural network canonical architecture, named Recurrent Trainable Neural Network (RTNN), suited for state-space systems identification, and an improved dynamic back-propagation method of its leaming, are proposed. The proposed R T " is studied with various representative examples and the results of its learning are compared with other results,, given in t...

There has been an increased interest in combining fuzzy systems with neural networks because fuzzy neural systems merge the advantages of both paradigms. On the one hand, parameters in fuzzy systems have clear physical meanings and rule-based and linguistic information can be incorporated into adaptive fuzzy systems in a systematic way. On the other hand, there exist powerful algorithms for tra...

In this paper, the impulsive fuzzy recurrent neural network with both time-varying delays and distributed delays is considered. Applying the idea of vector Lyapunov function, M-matrix theory and analytic methods, several sufficient conditions are obtained to ensure the existence, uniqueness and global exponential stability of equilibrium point for the addressed neural network. Moreover, the est...

A two-layer Recurrent Neural Network Model (RNNM) and an improved Backpropagation-through-time method of its learning are described. For a complex nonlinear plants identification, a fuzzy-neural multi-model, is proposed. The proposed fuzzy-neural model, containing two RNNMs is applied for real-time identification of nonlinear mechanical system. The simulation and experimental results confirm th...

A recurrent neural network–based forecasting system for telecommunications call volume is proposed in this work. In particular, the forecaster is a Block–Diagonal Recurrent Neural Network with internal feedback. Model’s performance is evaluated by use of real–world telecommunications data, where an extensive comparative analysis with a series of existing forecasters is conducted, including both...

Time series prediction is a problem with a wide range of applications, including energy systems planning, currency forecasting, stock exchange operations or traffic prediction. Accordingly, a number of different prediction approaches have been proposed such as linear models, Feedforward Neural network models, Recurrent Neural networks or Fuzzy Neural Models. In this paper one presents a predict...

This paper presents a comparative study of six soft computing models namely multilayer perceptron networks, Elman recurrent neural network, radial basis function network, Hopfield model, fuzzy inference system and hybrid fuzzy neural network for the hourly electricity demand forecast of Czech Republic. The soft computing models were trained and tested using the actual hourly load data obtained ...

The paper proposed to apply a hierarchical fuzzy-neural multi-model and Takagi–Sugeno (T–S) rules with recurrent neural procedural consequent part for systems identification, states estimation and adaptive control of complex nonlinear plants. The parameters and states of the local recurrent neural network models are used for a local direct and indirect adaptive trajectory tracking control syste...