This paper considers the use of neural networks to model bounded rational behaviour. The underlying theory and use of neural networks is now a component of various forms of scientific enquiry, be it modelling artificial intelligence, developing better pattern recognition or solving complex...

Companies in the S&P 500 produce quarterly financial statements that are closely studied by investors who forecast the stock market performance of those companies. This paper describes a Neural Logic Network (NLN) for predicting stock market returns based on financial ratios from financial...

This paper addresses the question of whether neural networks, a realistic cognitive model of the human information processing, can learn to backward induce in a two stage game with a unique subgame-perfect Nash Equilibrium. The result that the neural networks only learn a heuristic that...

This work describes an award winning approach for solving the NN3 Forecasting Competition problem, focusing on the sound experimental validation of its main innovative feature. The NN3 forecasting task consisted of predicting 18 future values of 111 short monthly time series. The main feature of...

This paper considers a sequence of misspecification tests for a flexible nonlinear time series model. The model is a generalization of both the Smooth Transition AutoRegressive (STAR) and the AutoRegressive Artificial Artificial Neural Network (AR-ANN) models. The tests are Lagrange multiplier...

In this paper, we propose a flexible smooth transition autoregressive (STAR) model with multiple regimes and multiple transition variables. We show that this formulation can be interpreted as a time varying linear model where the coefficients are the outputs of a single hidden layer feedforward...

If mental maps are a well-known subject in spatial analysis, they suffer from the difficulties to make them an operational concept. Nowadays, the development of cognitive science opens up new perspectives. Thanks to an association of spatial economists, roboticists and computer scientists in the...

This paper presents a neural network based methodology for examining the learning of game-playing rules in never-before seen games. A network is trained to pick Nash equilibria in a set of games and then released to play a larger set of new games. While faultlessly selecting Nash equilibria in...

Intelligent agents and multi-agent systems prove to be a promising paradigm for solving problems in a distributed, cooperative way. Neural networks are a classical solution for ensuring the learning ability of agents. In this paper, we analyse a multi-agent system where agents use different...