Recent Methodology in Connectionist Systems

Recent Methodology in Connectionist Systems

Ana B. Porto Pazos (University of A Coruña, Spain), Alberto Alvarellos González (University of A Coruña, Spain) and Alejandro Pazos Sierra (University of A Coruña, Spain)
DOI: 10.4018/978-1-59904-996-0.ch006

Abstract

The Artificial NeuroGlial Networks, which try to imitate the neuroglial brain networks, appeared in order to process the information by means of artificial systems based on biological phenomena. They are not only made of artificial neurons, like the artificial neural networks, but also they are made of elements which try to imitate glial cells. An important glial role related with the processing of the brain information has been recently discovered but, as the functioning of the biological neuroglial networks is not exactly known, it is necessary to test several and different possibilities for creating Artificial NeuroGlial Networks. This chapter shows the functioning methodology of the Artificial NeuroGlial Networks and the application of a possible implementation of artificial glia to classification problems.
Chapter Preview
Top

Background

The specific association of processes with synapses and the discovery of two-way astrocyte-neuron communication (Perea & Araque, 2005) have demonstrated the inadequacy of the previously held view regarding the purely supportive role for these glial cells. Instead, future progress requires rethinking how the dynamics of the coupled neuron-glial network can store, recall, and process information.

It is a novel research field that is here covered from the Artificial Intelligence viewpoint; no CS considering the glial system had been developed ever before.

In this regard, the RNASA (Artificial Neural Networks and Adaptive Systems) laboratory, our group from the University of A Coruña performs two interrelated research works from the viewpoint of Computer Science. One of these types involves the elaboration of “biological” computational models to reach a better understanding of the structure and behaviour of both neurons (LeRay et al., 2004, Fernández et al., 2007), and astrocytes (Porto, 2004). The second type of works considers behaviour observed in the brain circuits and the studied biological phenomena in order to create CSs; these systems should test if the presence of such phenomena provides advantages for information processing (Porto et al., 2005; Porto et al. 2006, Porto et al. 2007). No actualised publications of other research groups have been found regarding the later works, although some first attempts of incorporating the astrocyte functions are appearing, as the work of Xi Shen & Philippe De Wilde (2006). These authors model the increase of the blood flow within the brain capillary vessels according the neuronal activity and the neuron-astrocyte pairing; however, it is only a mathematical modelling that does not use the knowledge about astrocytes on the implementation of CSs.

Complete Chapter List

Search this Book:
Reset