Alberto Arteta

The optimal combination: Grammatical swarm, particle swarm optimization and neural networks

Social behaviour is mainly based on swarm colonies, in which each individual shares its knowledge about the environment with other individuals to get optimal solutions. Such co-operative model differs from competitive models in the way that individuals die and are born by combining information of alive ones. This paper presents the particle swarm optimization with differential evolution algorithm in order to train a neural network instead the classic back propagation algorithm. The performance of a neural network for particular problems is critically dependant on the choice of the processing elements, the net architecture and the learning algorithm. This work is focused in the development of methods for the evolutionary design of artificial neural networks. This paper focuses in optimizing the topology and structure of connectivity for these networks.

Solving complex problems with a bioinspired model

Abstract Membrane systems are parallel and bioinspired systems which simulate membranes behavior when processing information. As a part of unconventional computing, P-systems are proven to be effective in solving complex problems. A software technique is presented here that obtain good results when dealing with such problems. The rules application phase is studied and updated accordingly to obtain the desired results. Certain rules are candidate to be eliminated which can make the model improving in terms of time.

Usefulness States in New P System Communication Architectures

Dealing with distributed implementations of P systems, the bottleneck communication problem has arisen. When the number of membranes grows up, the network get congested. In agreement with this, several published works have presented an analysis for different architectures, which implement P systems in a distributed cluster of processors, allocating several membranes to the same processor. The purpose of these architectures is to reach a compromise between the massively parallel character of the system and the needed evolution step time to transit from one configuration of the system to the next one, solving the bottleneck communication problem. The work presented here carries out an analysis of semantics of the P systems, in several distributed architectures. It will be shown how to restructure P systems when dissolutions or inhibitions take place in membranes. Moreover, it will be also determined the extra information necessary at every communication step in order to allow all objects to arrive at their targets without penalizing the communication cost. This will be based on usefulness states, presented in a previous work, which allow each membrane of the system to know the set of membranes with which communication is possible at any time.