Abstract:

  Venn networks are computational intelligent architectures (i.e. a type of artificial neural network), proposed by the Buarque, which have the ability to mimic some brain function at the same time their internal activity resemble what is seen in functional imaging of the brain. Inspired by the morpho-functional organization of the brain, Venn-networks allow: (i) use of different type of processing units; (ii) definition of distinct regions within the network structure; (iii) use of a wide variety of connection type (among processing units); and, (iv) definition of a non-trivial connectivity based on the selection of fibers available.

  This research project aims at implementing (on the first generation of Venn-networks) a layered processing structure that includes competition, not only between processing units (i.e. cortical columns) but also, competition between layers.   

 

 Keywords: Artificial Neural Networks, Venn-Networks, Neural Network Simulators, Models of Cortex, Multilayer cortical organization, Brain function simulation

 People:

1.  Fernando Buarque de Lima Neto - Principal Investigator

2.  Amanda Leonel  - Undergraduate Research Student

3.  Hugo Serrano - Undergraduate Research Student

4.  Anderson Tenório Sérgio - Undergraduate Research Student

 

 Funding:

1. Two Undergraduate Research Students - Grant PIBIC - CNPq/UPE

2. CNPq Programme MCT/CNPq 15/2007-Universal-Faixa A.

 Period: August/2006 to July/2009.

 

 Place: CIRG - Polytechnic School of Engineering / Pernambuco State University - Recife - Brazil

 

 Hypotheses:

1. By adding extra processing layer to Venn-networks, their processing capabilities will increase markedly;

2. The ML-Venn maybe very useful for understanding inter-hemispheric communications & a tool for prognosis in neurology;

 Context: A new and promising frontier in neuroscience lies on a better understanding of the layered structure of the cortex (RAIZADA, 2003). Some scientists, based on anatomo-physiological evidences of the brain, stand that the cortical evolution, to its multi-layered organization in primates, grants them with an overwhelming additional processing power (TREVES, 2003).

 

 Expected results:

1. To find out how to build the algorithmic solution for including a multilayered processing structure in Venn-networks;

2. To assess the increase of processing capabilities of Venn-network due to the extra layers added-on;

3. To find out new usage for the new family of neural networks, ML-Venn, resulting of this research;

4. To build another version of the Venn-network simulator that incorporates multilayer processing abilities.

 Conclusions: the research results have shown that:

1. WORK IN PROGRESS

Original contribution: the original contribution of this research, produced by independent scientific research pursued by the author & team, is listed below  To the best of their knowledge the ideas and results mentioned here are original:

 

     Resumo: 1) Why including more Processing-Layers in Venn-Networks? II Simpósio Internacional de Neurociências do IINN - Natal/Brasil. Fev/2007   

 

Other Scientific Production: the research results also were used to produce:

1. Picture Galery of ML-Venn Project

2. WORK IN PROGRESS