Henrique E. Borges

A model for hierarchical associative memories via dynamically coupled GBSB neural networks

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.

Information storage and retrieval analysis of hierarchically coupled associative memories

This paper presents information storage and retrieval analysis as well as energy analysis of a multi-level or hierarchically coupled associative memory based on coupled generalised-brain-state-in-a-box (GBSB) neural networks. In this model, the memory processes are described as being organised functionally in hierarchical levels where higher levels coordinate sets of functions of the lower levels. We consider the case where lowest level subnetworks have predefined attractors, prior to imposing their association through imprinting synapses between them. Simulations are carried out using linearly independent (Li) and orthogonal vectors considering a wide range of parameters. The results obtained show that, even when the neural networks are weakly coupled, the system still presents a significant convergence to global patterns, mainly in orthogonal vectors.

A multiagent architecture for solving combinatorial optimization problems through metaheuristics

This article introduces MAM - multiagent architecture for metaheuristics, whose objective is to combine metaheuristics, through the multiagent approach, for solving combinatorial optimization problems. In this architecture, each metaheuristic is developed in the form of an autonomous agent, cooperatively interacting in an environment. This interaction between one or more agents is carried out through information exchange in the search space of the problem, seeking to improve the same objective. MAM is a flexible architecture, which can be used for solving different optimization problems, without the need to rewrite algorithms. In this paper, the MAM architecture is specialized for genetic algorithm (GA), iterated local search (ILS) and variable neighborhood search (VNS) metaheuristics in order to solve the vehicle routing problem with time windows (VRPTW). Computational tests were performed and results are presented, showing the effectiveness of the proposed architecture.

Space-vector structure based synthesis for hierarchically coupled associative memories

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.

Emergence of Neuronal Groups on a Self-Organized Spiking Neurons Network Based on Genetic Algorithm

Based on the Theory of Neuronal Group Selection (TNGS), proposed by Edelman, a network composed of one hundred Izhikevich spiking neurons is analyzed. In this study, a genetic algorithm is used to estimate the Izhikevich neuron model parameters in order to enable the self-organization of a neural network into a cluster of tightly coupled neural cells which fire and oscillate in synchrony at a predefined frequency.

Storage capacity of hierarchically coupled associative memories

This paper, taking as inspiration the ideas proposal for the TNGS (Theory of Neuronal Group Selection), presents a study of convergence capacity of two-level associative memories based on coupled Generalized-Brain-State-in-a-Box (GBSB) neural networks. In this model, the memory processes are described as being organized functionally in hierarchical levels, where the higher levels would coordinate sets of function of the lower levels. Simulations were carried out to illustrate the behaviour of the capacity of the system for a wide range of the system parameters considering linearly independent (LI) and orthogonal vectors. The results obtained show the relations amongst convergence, intensity and density of coupling.

A scalable methodology to measure power distribution networks reliability

Power distribution networks are increasing, more complex and therefore should provide maximum reliability to its customers. Susceptible to interruptions, defects and malfunction for various reasons, investments in improving distribution network quality are increasing and should be performed based on environment conditions, technical requirements, demands and needs. This paper presents a new methodology to measure and evaluate distribution networks reliability degree based on historical failure data, maintenance costs and variable depreciation study. The new index developed in this effort works as an aid tool to minimize the investment in distribution network maintenance and can be used to predict the value of SAIFI indicator after systematic exchanges, since this it is a worldwide metric for assessing electric power quality and both share the same information.

Emergence of synchronicity in a self-organizing spiking neuron network: an approach via genetic algorithms

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.

Synthesis of frequency generator via spiking neurons network: A genetic algorithm approach

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.

Construção De Detector De Estímulo Com Neurônio Pulsante Via Evolução Diferencial

Computational neuroscience seeks to understand the mechanisms and functions of the nervous system through the construction of realistic mathematical models of neural networks and the realization of large-scale computer simulations. However, the creation of these mechanisms are still a distant reality, and thus, current research has sought to reproduce, in general, simple tasks of the nervous system. Therefore, The Izhikevich spiking neuron model was chosen because of their excellent performance computing, while preserving many of the desirable biological features. Thus, this paper proposes the construction of detectors based on Izhikevich spiking neuron model, who are able to detect external stimuli, i.e., to pulse when they are stimulated by current pulses from the external environment. For this, we have performed a set of simulations involving tuning the parameters of the Izhikevich spiking neuron model, as well as tuning the magnitude of current stimulation via the method of differential evolution optimization. As a result, it was possible to find a set of solutions that automatically adjust the parameters of the spiking neuron, so that it behaves as a stimuli detector. Furthermore, based on sample average rate of correct solutions obtained in the first set of simulation, four among the best solutions were selected in order to validate and analyze the average success rates depending on the values of probability of occurrence of stimuli. It is hoped that these results will contribute to a better analysis of the behavior of artificial neurons in the construction of sensors with greater biological plausibility.