Gonzalo Joya Caparrós

Continuous-State Hopfield Dynamics Based on Implicit Numerical Methods

A novel technique ispres ented that implementscon tinuousstate Hopfield neural networks on a digital computer. Instead of the usual forward Euler rule, the backward method is used. The stability and Lyapunov function of the proposed discrete model are indirectly guaranteed, even for reasonably large step size. This is possible because discretization by implicit numerical methodsinheritsthe stability of the continuoustime model. On the contrary, the forward Euler method requiresa very small step size to guarantee convergence to solutions. The presented technique takes advantage of the extensive research on continuous-time stability, asw ell asrecen t resultsin the field of dynamical analysisof numerical methods. Also, standard numerical methods allow for synchronous activation of neurons, thus leading to performance enhancement. Numerical results are presented that illustrate the validity of this approach when applied to optimization problems.

Neural Networks for Contingency Evaluation and Monitoring in Power Systems

In this paper an analysis of the applicability of different neural paradigms to contingency analysis in power systems is presented. On one hand, unsupervised Self-Organizing Maps by Kohonen have been implemented for visualization and graphic monitoring of contingency severity. On the other hand, supervised feed-forward neural paradigms such as Multilayer Perceptron and Radial Basis Function, are implemented for severity numerical evaluation and contingency ranking. Experiments have been performed with successfully result in the case of Kohonen and Multilayer Perceptron paradigms.

Early pigmentary retinosis diagnostic based on classification trees

In this work we analyze different classification tree based techniques (CART, Bagging and Boosting), evaluating their performance with respect to their capability to reduce error rate and correct pattern classification. As a case of study we propose the classification of Pigmentary Restinosis patients through electroretinograms. Pigmentary Restinosis is the most frequent retina dystrophy (1/5000). The electroretinogram (ERG) constitutes a fundamental test in the study of this type of dystrophy since the wide clinical heterogeneity of visual diseases. Besides, retina electrophysiological study can provided information that may be used to predict the disease before the apparition of symptoms and allows us to corroborate the affectation degree on the dystrophic process of cones and canes. As experimental database we use a set of 148 electroretinograms, which is part of a retrospective study carried out by the Cuban National Reference Center of Pigmentary Retinosis.

Adaptation of Deep Convolutional Neural Networks for Cancer Grading from Histopathological Images

The paper addresses the medical challenge of interpreting histopathological slides through expert-independent automated learning with implicit feature determination and direct grading establishment. Deep convolutional neural networks model the image collection and are able to give a timely and accurate support for pathologists, who are more than often burdened by large amounts of data to be processed. The paradigm is however known to be problem-dependent in variable setting, therefore automatic parametrization is also considered. Due to the large necessary runtime, this is restricted to kernel size optimization in each convolutional layer. As processing time still remains considerable for five variables, a surrogate model is further constructed. Results support the use of the deep learning methodology for computational assistance in cancer grading from histopathological images.