Artificial Neural Networks: An Overview and their Use in the Analysis of the AMPHORA-3 Dataset

Abstract

The Artificial Adaptive Systems (AAS) are theories with which generative algebras are able to create artificial models simulating natural phenomenon. Artificial Neural Networks (ANNs) are the more diffused and best-known learning system models in the AAS. This article describes an overview of ANNs, noting its advantages and limitations for analyzing dynamic, complex, non-linear, multidimensional processes. An example of a specific ANN application to alcohol consumption in Spain, as part of the EU AMPHORA-3 project, during 1961–2006 is presented. Study's limitations are noted and future needed research using ANN methodologies are suggested.

Keywords :

• artificial neural networks
• artificial adaptive systems
• supervised and unsupervised ANNs

Notes

1 This relatively new term, introduced into the intervention literature by Friedman et al. (Samuel R. Friedman, Diana Rossi, Peter L. Flom. (2006). “Big events” and networks: Thoughts on what could be going on. Connections 27(1): 9–14.) refers to major events, such as mega-disasters, natural, as well as man-made, famine, conflict, genocide, disparities in health, epidemics, mass migrations, economic recessions, etc. which effect adaptation, functioning and quality-of-life of individuals as well as systems. Existential threat, instability and chaos are major dimensions and loss of control over one's life is experienced