Free Access
Issue
E.J.E.S.S.
Volume 15, Number 3, 2001
Evolution and Learning in Markets
Page(s) 203 - 220
DOI https://doi.org/10.1051/ejess:2001105
DOI: 10.1051/ejess:2001105


European Journal of Economic and Social Systems 15 N°3 (2001) 203-220

Connecting adaptive behaviour and expectations in models of innovation: The Potential Role of Artificial Neural Networks

Murat Yildizoglu

IFREDE-E3I, Université Montesquieu Bordeaux IV, Avenue Leon Duguit, F-33608 Pessac, France. yildi@montesquieu.u-bordeaux.fr

Abstract
In this methodological work I explore the possibility of explicitly modelling expectations conditioning the R&D decisions of firms. In order to isolate this problem from the controversies of cognitive science, I propose a black box strategy through the concept of "internal model". The last part of the article uses artificial neural networks to model the expectations of firms in a model of industry dynamics based on Nelson & Winter (1982).


Key words: Neural networks, genetic algorithms, bounded rationality, learning, expectations, innovation dynamics.


© EDP Sciences 2001

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.