Henrique Borges

Inspired by the theory of neuronal group selection (TNGS), we have carried out an analysis of the capacity of convergence of a multi-level associative memory based on coupled generalized-brain-state-in-a-box (GBSB) networks through evolutionary computation. The TNGS establishes that a memory process can be described as being organized functionally in hierarchical levels where higher levels coordinate sets of functions of lower levels. According to this theory, the most basic units in the cortical area of the brain are called neuronal groups or first-level blocks of memories and the higher-level memories are formed through selective strengthening or weakening of the synapses amongst the neuronal groups. In order to analyse this effect, we propose that the higher levels should emerge through a learning mechanism as correlations of lower level memories. According to this proposal, this paper describes a method of acquiring the inter-group synapses based on a genetic algorithm. Thus the results show that genetic algorithms are feasible as they allow the emergence of complex behaviours which could be potentially excluded in other learning process.

A new methodology for the parameterization of the technical analysis of the financial market indicator coined Moving Average Convergence-Divergence (MACD) is presented in this paper. The architecture of the MACD involves the use of exponential moving averages that in turn use different time windows, tracking securities prices trends and signaling the right moment to purchase and sell the shares. By using genetic algorithms, it is possible to establish an optimal value for the time window which could yield higher profits when compared to the time window used in literature. The use of fuzzy logic indicates the best moment for purchase and sale of shares, improving the security of each transaction, thus resulting in increased success rate. The methodology proposed is validated by taking into account the Petrobras shares (PETR4) in the period between February 2005 and August 2008 when such methodology led a profit higher than that yielded in the usual parameterisation.

Based on the Theory of Neuronal Group Selection (TNGS), we have investigated the emergence of synchronicity in a network composed of spiking neurons via genetic algorithm. The TNGS establishes that a neuronal group is the most basic unit in the cortical area of the brain and, as a rule, it is not formed by a single neuron, but by a cluster of tightly coupled neural cells which fire and oscillate in synchrony at a predefined frequency. Thus, this paper describes a method of tuning the parameters of the Izhikevich spiking neuron model through genetic algorithm in order to enable the self-organization of the neural network. Computational experiments were performed considering a network composed of neurons of the same type and another composed of neurons of different types.

Inspired by the Theory of Neuronal Group Selection (TNGS), we have carried out synthesis of frequency generator via spiking neurons network through genetic algorithm. The TNGS sets that a neuronal group is the most basic unit in the cortical area and are generated by synapses of localized neural cells in the cortical area of the brain firing and oscillating in synchrony at a predefined frequency. Each one of these clusters (Neuronal Groups) is a set of localized, tightly coupled neurons developed in the embryo. According to this proposal, this paper describes a method of tuning the parameters of the Izhikevich spiking neuron model. Computational experiments consisting of a network with all neurons of the same type and a network with different neurons were conducted. A genetic algorithm was used to tune the parameters in these two different cases. The results were compared in order to find the best way to create a frequency generator of spiking neurons network.

The present work introduces a proposal for the training of hierarchically coupled associative memories. The method is based on the eigenvalue and eigenvector structure of the space-vector and on suitable changes the space basis. The approach shows to be useful to the class of models hierarchically coupled associative memories, which has the memorization process organized in many levels of degreesof- freedom and for which the training behaves as a synthesis of previously desired states.

Many approaches have emerged in the attempt to explain the memory process. One of which is the Theory of Neuronal Group Selection (TNGS), proposed by Edelman [1]. In the present work, inspired by Edelman ideas, we design and implement a new hierarchically coupled dynamical system consisting of GBSB neural networks. Our results show that, for a wide range of the system parameters, even when the networks are weakly coupled, the system evolve towards an emergent global associative memory resulting from the correlation of the lowest level memories.