Eliezer Colina-Morles

Sliding mode-based adaptive learning in dynamical-filter-weights neurons

A sliding mode control strategy is proposed for the synthesis of an adaptive learning algorithm in a neuron whose weights are constituted by first-order dynamical filters with adjustable parameters, which in turn allows the representation of dynamical processes in terms of a set of such neurons. The approach is shown to exhibit robustness characteristics and fast convergence properties. A simulation example, dealing with an analog signal tracking task, is provided which illustrates the feasibility of the approach.

Sliding mode-based adaptive learning in dynamical Adalines

A sliding mode control strategy is proposed for the synthesis of adaptive learning algorithms in perceptron-based feedforward neural networks whose weights are constituted by first order, time-varying, dynamical systems with adjustable parameters. The approach is shown to exhibit strong robustness and fast convergence properties. A simulation example, dealing with an analog signal tracking task, is provided, which illustrates the feasibility of the approach.

Neuronmaster: an integrated tool for applications in neural networks

This work presents the design of an integral environment for the suitable development of neural networks applications. The integrated environment contemplates the following features: A data processing module which encompasses statistical data analysis techniques for variables selection reduction, a variety of learning algorithms, code generator for different computer languages to enable network implementation, a learning sessions planning module and database connectivity facilities via ODBC, RPC, and API.

Identification and control of nonlinear systems using neural networks with variable-structure-control-based learning algorithms

This paper presents a Variable Structure Control VSC-based algorithm for adjusting a set of time varying parameters of virtual linear models that resemble linear dynamical neurons, used as on-line representations for a class of uncertain nonlinear processes. These virtual linear models allow the implementation of adaptive controllers in order to achieve predefined specifications for the closed-loop of the uncertain nonlinear process, or to force the tracking of the process output to reference models outputs accurately. A proof of the finite time convergence of the virtual linear model variables to the uncertain nonlinear process variables is included and some examples are contemplated to illustrate the proposed control design approaches.

Fault diagnosis hybrid system using a Luenberger-based detection filter and neural networks

The present paper proposes a new layout for failure detection and diagnosis in industrial dynamic systems in which, failure vector decoupling is not always possible, due to the failure intrinsic propagation. In this case diagnosis can be determined due to the existing correlation between the failure vector and residual vector time patterns. The greatest benefit of this study is the failure detection method, Luenberger observer based detection filter, through vectorial residual generation combined with the pattern recognition technique based on neural networks theory. The synergy of both methods offer a wider application range to diagnosis problem solutions, in systems under presence of non-decoupled failures.

Methodology for implementing Virtual Sensors using Neural Networks

In this work a Methodology framework for implanting Virtual Sensors using Neural Networks will be presented, including the statistical analysis techniques that can be used for studying and processing the data. The proposed Methodology is based upon Software Engineering, Knowledge-based systems and neural networks methodologies. This methodological framework includes both technical and economical feasibility to build the virtual sensors and considers important aspects as the available computational platform, historical data files, data processing requirements such as filtering, pruning, set of variables that must be selected for the best performance of the virtual sensor, etc. There are also presented the statistical consideration and the corresponding techniques for data analysis and processing. The methodology includes techniques as principal components, cluster analysis, factorial analysis, etc.

Dynamic neuron-VSC-based adaptive control of uncertain nonlinear systems

Abstract A Variable Structure Control (VSC) based algorithm is used for adjusting a set of time varying parameters of a linear dynamic neuron, that serves as a model tor an uncertain nonlinear system with measurable state vector. This model allows the implementation of adaptive controllers in order to achieve predefined specifications for the closed loop system. Two computer simulated examples are presented to illustrate the proposed approach

Variable structure control based on-line learning design for continuous time multilayer networks

The purpose of this paper is to introduce variable structure-based-on-line learning algorithms for continuous time two layer and three layer perceptron networks with non-linear and linear activation functions. The computer implementation of the proposed algorithms result in a temporal learning capabilities of a neural network with dynamically adjusted weights, and zero convergence of the learning error in a finite time. The performance of the considered networks is tested in terms of solving a tracking problem of a sine signal.

A Sliding Mode Strategy for Adaptive Learning in Adalines

Abstract A dynamical sliding mode control approach is proposed for robust adaptive learning in analog Adaptive Linear Elements (Adalines), constituting basic building blocks for perceptron-based feedforward neural networks. The zero level set of the learning error variable is regarded as a sliding surface in the space of learning parameters. A sliding mode trajectory can then be induced, in finite time, on such a desired sliding manifold. Neuron weights adaptation trajectories are shown to be of continuous nature, thus avoiding bang-bang weight adaptation procedures.