Neural Networks, Game Theory and Time Series Generation
arXiv:cond-mat/0212486
Abstract
This dissertation highlights connections between the fields of neural networks, game theory and time series generation. The concept of antipredictability is explained, and the properties of time series that are antipredictable for several prototypical prediction algorithms (neural networks, Boolean funtions etc.) are studied. The Minority Game provides a framework in which antipredictability arises naturally. Several variations of the MG are introduced and compared, including extensions to more than two choices, and the properties of the generated time series are analysed. A learning algorithm is presented by which a neural network can find a good mixed strategy in zero-sum matrix games. In a certain limit, this algorithm is a stochastic variation of the "fictitious play" learning algorithm.
Dissertation. 130 pages, quite a few figures
References in corpus (22)
- Statistical mechanics of systems with heterogeneous agents: Minority Games
- Irrelevance of memory in the minority game
- Phase Transition and Symmetry Breaking in the Minority Game
- Self-Organized Segregation within an Evolving Population
- From market games to real-world markets
- Theory of the evolutionary minority game
- Matrix Games, Mixed Strategies, and Statistical Mechanics
- Continuous time dynamics of the Thermal Minority Game
- Self-Averaging and On-line Learning
- Learning and predicting time series by neural networks
- Statistical mechanics of random two-player games
- A New Stochastic Strategy for the Minority Game
- Multi-Choice Minority Game
- Elementary constraints on autocorrelation function scalings
- Low autocorrelated multi-phase sequences
- Limit cycles of a perceptron
- Long-term properties of time series generated by a perceptron with various transfer functions
- Generation of unpredictable time series by a Neural Network
- Crowd-anticrowd model of the Minority Game
- Noisy time series generation by feed-forward networks
- Competing neural networks: Finding a strategy for the game of matching pennies
- Jamming transitions and avalanches in the game of Dots-and-Boxes