1,721,063 research outputs found
Feedforward networks in financial predictions: The future that modifies the present
No full textThe main goal of this paper is to show how relatively minor modifications of well-known algorithms (in particular, back propagation) can dramatically increase the performance of an artificial neural network (ANN) for time series prediction. We denote our proposed sets of modifications as the `self-momentum', `Freud' and `Jung' rules. In our opinion, they provide an example of an alternative approach to the design of learning strategies for ANNs, one that focuses on basic mathematical conceptualization rather than on formalism and demonstration. The complexity of actual prediction problems makes it necessary to experiment with modelling possibilities whose inherent mathematical properties are often not well understood yet. The problem of time series prediction in stock markets is a case in point. It is well known that asset price dynamics in financial markets are difficult to trace, let alone to predict with an operationally interesting degree of accuracy. We therefore take financial prediction as a meaningful test bed for the validation of our techniques. We discuss in some detail both the theoretical underpinnings of the technique and our case study about financial prediction, finding encouraging evidence that supports the theoretical and operational viability of our new ANN specifications. Ours is clearly only a preliminary step. Further developments of ANN architectures with more and more sophisticated `learning to learn' characteristics are now under study and test
What kind of ‘world order’? An artificial neural networks approach to intensive data mining
No full textIn this paper, we present an innovative data processing architecture, the Activation & Competition System (ACS), and show how this methodology allows us to reconstruct in detail some aspects of the fine grained structure of global relationships in the world order perspective, on the basis of a minimal dataset only consisting of the values of five publicly available indicators for 2007 for the 118 countries for which they are jointly available. ACS seems in particular to qualify as a valuable tool for the analysis of inter-country patterns of conflict and alliances, which may prove of special interest in the current situation of global strategic uncertainty in international relations
A neural Network investigation on the crucial Assets of urban Sustainability
No full textSpecial Issue on Artificial Neural Networks and Social System
Urban sustainability: complex interactions through neural network approach
No full textISBN 88-464-1685-
Multidimensional Similarities at a Global Scale: An Approach to Mapping Open Society Orientations
No full textThis paper analyzes the global geography of open society orientations in the sense of Karl Popper’s notion of open society, by means of a database consisting of five common, public and widely used indicators such as UNDP’s Human Development Index, the World Economic Forum’s Global Competitiveness Index, the Heritage Foundation’s Economic Freedom Index, Reporters Sans Frontières’ Press Freedom Index, and Transparency International’s Corruption Perception Index. We carry out a cluster analysis based on the Self-Organizing Map (SOM) technique, and find that the geography of open society orientation organizes globally into four main clusters with distinctive socio-economic characteristics. We discuss the implications of the clusterization and find that it provides interesting insight also as to the post-2008 response of countries to the global financial crisis
Complexity in Sustainability: an Investigation of the Italian Urban System trough Self-Reflexive Neural Networks
No full text
- …
