No abstract

No abstract

Alzheimer's disease is a degenerative disorder of the brain that is still without cure and affects millions of people around the world. Understanding the disease mechanisms is important for therapeutics. A first step would be to use an explanatory model of the disease's symptoms. For that one would need an adaptive computational approach that resembles the biological system, upon which the Alzheimer's lesions like are to be simulated. Artificial Neural Networks may function as the needed test bed; Venn network is an artificial neural network (ANN) that has capability of simulating the behavior of a functioning brain under physiological and pathological scenarios. Hopfield network is another ANN that can recover previously stored patterns. This paper aims at presenting a computational approach that combines Venn and Hopfield networks in order to model of Alzheimer's disease. During the modeling phase, we have developed an artificial neural network structure based on Venn networks and the training algorithm of standard Hopfield model. The neural network was trained to recognize certain patterns of training, in this case, binary images. On top of that the Alzheimer's disease was modeled computationally taking into consideration some of its neuropathological aspects. Throughout various simulations, we have found that the Alzheimer's disease model disturbed the performance of a regular trained neural network, thus mimicking the pathological effects in the human brain.

No abstract

Compact evolutionary algorithms have proven to be an efficient alternative for solving optimization problems in computing environments with low processing power. In this kind of solution, a probability distribution simulates the behavior of a population, thus looking for memory savings. Several compact algorithms have been proposed, including the compact genetic algorithm and compact differential evolution. This work aims to investigate the use of compact approaches in other important evolutionary algorithms: evolution strategies. This paper proposes two different approaches for compact versions of evolution strategies. Experiments were performed and the results analyzed. The results showed that, depending on the nature of problem, the use of the compact version of Evolution Strategies can be rewarding.