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)
In this exploratory work we attempt to understand and to measure the notion of complex structure in networks. The first section discusses the ill-defined notion of complexity and describes the quantitative tools that we will use in an attempt to tie it down. In the second section we describe our attempts at relating these measures of structural complexity(More)
This paper introduces a new hybrid approach for learning systems that builds on the theory of nonextensive statistical mechanics. The proposed learning scheme uses only the sign of the gradient, and combines adaptive stepsize local searches with global search steps that make use of an annealing schedule inspired from nonextensive statistics, as proposed by(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)
This paper introduces an efficient modification of the Rprop algorithm for training neural networks. The convergence of the new algorithm can be justified theoretically, and its performance is investigated empirically through simulation experiments using some pattern classification benchmarks. Numerical evidence shows that the algorithm exhibits improved(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)
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)
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)