The problem of controlling a discrete-time nonlinear non-minimum phase system is considered in this paper. An output re-definition strategy is developed which is applicable to a class of open-loop stable nonlinear systems whose input-output maps contain ...

In this work, a neural network control procedure is presented which performs discrete-time constrained optimal control of non-linear systems. Different neural network structures are tested, and different control error functions are used as network ...

We study, using standard Probability Theory results, the ability of the Hopfield model of associative memory using the Hebb rule to learn mean values from examples in the presence of noise. We state and prove properties concerning this ability.

An unsupervised neural network that uses Hebbian and anti-Hebbian learning (HAHL model) was implemented to determine levels of anxiety of rats by clustering these animals based on their behavior in the elevated plus maze. The HAHL model showed capacity ...

Ovarian cancer has been the leading cause of death from gynecologic cancer in the United States. Seventy percent of women with ovarian cancer have advanced disease at diagnosis, which has resulted a low 5-year survival rate (\math30%) with no ...

The QUEEN 1 method is based on four main concepts: 1. The QUEEN phase model is derived from the spiral model of Böhm and integrates the development of a neural network. 2. An overall strategy for the development process enables a continuous supervision, ...

We apply artificial neural networks to identify global health inequalities of 191 WHO countries by clustering them into eight groups. From this, we are able to provide key indicators for the health promotion direction for these countries.

An hexapod, or Stewart, platform consists essentially of two platforms and six extensible linear actuators (legs), each one connected to the platforms with a couple of universal joints, one at each end. In the last years, several applications have been ...

In this paper we use a uniformity property of Riemann integration to obtain a single-hidden-layer neural network of fixed translates of a (not necessarily radial) basis function with a fixed width that approximates a (possibly infinite) set of target ...

Sensitivity analysis is a method for extracting the cause and effect relationship between the inputs and outputs of the network. After training a neural network, one may want to know the effect that each of the network inputs is having on the network ...

We present a probabilistic neural network model, which is suitable for classification problems. This model constitutes an adaptation of the classical RBF network where the outputs represent the class conditional distributions. Since the network outputs ...

Juan I. Godino-Llorente and Santiago Aguilera-NavarroETSIWe present a neural network application to the diagnosis of vocal and voice disorders, these disorders should be diagnosis in the early stage and normally cause changes in the voice signal. ...

Low-power low-voltage mixed-analog/digital-signal CMOS technology is used in implementing a novel dynamic-synapse neural network microchip. A basic building block for dynamic process is implemented with a variable current source, resistors, charging/...

This paper presents a simple continuous analog hardware realization of the Random Neural Network (RNN) model. The proposed circuit uses the general principles resulting from the understanding of the basic properties of the firing neuron. The circuit for ...

In our contribution, we investigate how structured information processing within a neural net can emerge because of unsupervised learning from data. Our model consists of input neurons and hidden neurons which are recurrently connected and which ...

We describe here how a network of oscillators can perform neural computations. In particular, it showed how the connectivity within the network could be created to memorize data in terms of phase relations between synchronized states. The memorized ...

We propose a new self-creating and self-organizing neural networks utilizing weight duplication. It is well known that columnar structures in the brain play a great role in visual information processing of early vision. In a columnar network, there are ...

We have previously [4] derived a neural network implementation of the statistical technique of Canonical Correlation Analysis (CCA). We extend this to nonlinear CCA either by adding a non-linearity to our neural method or by nonlinearly transforming the ...

In our studies of the capabilities of neural networks, we have relied on time-lagged recurrent neural networks (TLRNN) to learn to emulate the behavior of complex dynamic systems. Since the data was derived from observation of actual physical plants, ...

This paper extends previous analysis of the gradient decay to a class of discrete-time recurrent networks, called Dynamical Recurrent Neural Networks (DRNN), obtained by modeling synapses as Finite Impulse Response (FIR) filters instead of ...