Aristoklis D. Anastasiadis

Learn More
In this paper, a new globally convergent modification of the Resilient Propagation-Rprop algorithm is presented. This new addition to the Rprop family of methods builds on a mathematical framework for the convergence analysis that ensures that the adaptive local learning rates of the Rprop's schedule generate a descent search direction at each iteration.(More)
Membrane protein functioning basically depends on the supramolecular structure of the proteins which can be modulated by specific interactions with external ligands. The effect of a water-soluble protein bearing specific binding sites on the kinetics of ionic channels formed by gramicidin A (gA) in planar bilayer lipid membranes (BLM) has been studied using(More)
Scientists involved in the area of proteomics are currently seeking integrated, customised and validated research solutions to better expedite their work in pro-teomics analyses and drug discoveries. Some drugs and most of their cell targets are proteins, because proteins dictate biological phenotype. In this context, the automated analysis of protein(More)
In this work we have studied the research activity for countries of Europe, Latin America and Africa for all sciences between 1945 and November 2008. All the data are captured from the Web of Science database during this period. The analysis of the experimental data shows that, within a nonextensive thermostatistical formalism, the Tsallis q-exponential(More)
We show that the Cellular Automaton (CA) model for Solar flares of Lu and Hamilton (1991) can be understood as the solution to a particular partial differential equation (PDE), which describes diffusion in a localized region in space if a certain instability threshold is met, together with a slowly acting source term. This equation is then compared to the(More)
In this paper, inspired from our previous algorithm, which was based on the theory of Tsallis statistical mechanics, we develop a new evolving stochastic learning algorithm for neural networks. The new algorithm combines deterministic and stochastic search steps by employing a different adaptive stepsize for each network weight, and applies a form of noise(More)
Cellular automata (CA) models account for the power-law distributions found for solar flare hard X-ray observations, but their physics has been unclear. We examine four of these models and show that their criteria and magnetic field distribution rules can be derived by discretizing the MHD diffusion equation as obtained from a simplified Ohm's law.(More)
There are so many existing classification methods from diverse fields including statistics, machine learning and pattern recognition. New methods have been invented constantly that claim superior performance over classical methods. It has become increasingly difficult for practitioners to choose the right kind of the methods for their applications. So this(More)
This paper introduces a new class of sign-based training algorithms for neural networks that combine the sign-based updates of the Rprop algorithm with the composite nonlinear Jacobi method. The theoretical foundations of the class are described and a heuristic Rprop-based Jacobi algorithm is empirically investigated through simulation experiments in(More)