Recurrent neural networks of binary stochastic units with a general distribution function are studied using Markov chains theory. Sufficient conditions for ergodicity are established and under some assumptions, the stationary distribution is determined. The relation between fixed points and absorbing states is studied both theoretically and through simulations. For numerical studies the notion ...

In this paper, we provide a survey of recent advances in the field “Grammatical Inference” with a particular emphasis on the results concerning the learnability of target classes represented by deterministic finite automata, context-free grammars, hidden Markov models, stochastic contextfree grammars, simple recurrent neural networks, and case-based representations.

Fuzzy neural network methods have been successfully used to diagnose many diseases. This paper uses logic-based fuzzy neural networks to diagnose breast cancer. Logic-based fuzzy neural networks can select reduced size of input subspace by selecting useful inputs. For the optimization of the input subspace and the structure of the logic-based fuzzy neural networks, genetic algorithms and gradie...

This paper investigates some properties of Takagi-Sugeno (T-S) fuzzy Hopfield neural networks. First, we prove that there exists a unique solution of the T-S fuzzy Hopfield neural network. Second, we determine a condition for input-to-state stability (ISS) of the T-S fuzzy Hopfield neural network. These results will be useful to analyze dynamic behavior of fuzzy neural networks.

A fuzzy neural network and its relevant fuzzy neuron and fuzzy learning algorithm are introduced. An object-oriented implementation of fuzzy neural network in MATLAB environment is realized. Simulations are carried out by SIMULINK. The performance of fuzzy neural network is experimentally compared with other neural networks trained by backpropagation algorithms. It shows better convergence spee...

In this paper, the gain in LD-CELP speech coding algorithm is predicted using three neural models, that are equipped by genetic and particle swarm optimization (PSO) algorithms to optimize the structure and parameters of neural networks. Elman, multi-layer perceptron (MLP) and fuzzy ARTMAP are the candidate neural models. The optimized number of nodes in the first and second hidden layers of El...

We evaluate the performance of a heterogeneous mixture of neural network algorithms for predicting the exchange-traded fund DIA. A genetic algorithm is utilized to find the best mixture of neural networks, the topology of individual networks in the ensemble, and to determine the features set. The genetic algorithm also determines the window size of the input time-series supplied to the individu...

This paper reviews the basics of the von Neumann stochastic data representation and its application to the development of digital neural network and fuzzy logic controller architectures.

In this paper, we propose a generic and simple algorithmic framework for first order optimization. The framework essentially contains two consecutive steps in each iteration: 1) computing and normalizing the mini-batch stochastic gradient; 2) selecting adaptive step size to update the decision variable (parameter) towards the negative of the normalized gradient. We show that the proposed approa...