Neural Networks for Non-independent Lotteries
The von Neuman-Morgenstern utility functions play a relevant role in the set of utility functions. This paper shows the density of the set von Neuman- Morgenstern utility functions on the set of utility utility function that can represent arbitrarily well a given continuous but not independent preference relation over monetary lotteries. The main result is that without independence it is possible to approximate utility functions over monetary lotteries by von Neuman-Morgenstern ones with arbitrary precision. The approach used is a constructive one. Neural networks are used for their approximation properties in order to get the result, and their functional form provides both the von Neumann-Morgenstern representation and the necessary change of variables over the set of lotteries.
Unable to display preview. Download preview PDF.
- 1.Aliprantis, C.D., Chakrabarti, S.K.: Games and decision Making. Oxford Univ. Press, Oxford (1999)Google Scholar
- 2.Aliprantis, C.D., Chakrabarti, S.K.: Games and decision Making. Oxford Univ. Press, Oxford (1999)Google Scholar
- 3.Mas-Colell, A., Whinston, M.D., Green, J.R.: Microeconomic Theory. Oxford Univ. Press, Oxford (1995)Google Scholar
- 4.Rotundo, G.: Neural Networks for Partitionable Variational Inequalities. In: Proceedings of the APL 1998 (Array Parallel Processing) Conference, Rome (1998)Google Scholar
- 5.Rotundo, G.: Trasformazione di disequazioni variazionali in disequazioni variazionali partizionabili mediante reti neurali. In: XXIII A. M. A. S. E. S. Conference, Rende (1999)Google Scholar
- 6.Ripley, B.D.: Pattern recognition and Neural Netowrks. Cambridge University Press, Cambridge (1996)Google Scholar