Bayesian statistics is has been very successful in describing behavioural data on decision making and cue integration under noisy circumstances. However, it is still an open question how the human brain actually incorporates this functionality. Here we compare three ways in which Bayes rule can be implemented using neural fields. The result is a truly dynamic framework that can easily be extend...

In a Bayesian approach to online learning a simple approximate parametric form for posterior is updated in each online learning step. Usually in online learning only an estimate of the solution is updated. The Bayesian online approach is applied to two simple learning scenarios, learning a perceptron rule with respectively a spherical and a binary weight prior. In the rst case we rederive the r...

In this paper ongoing work on an approach for planning sensing actions and controlling intelligent, purposive robotic systems is presented. The method uses Bayesian Decision Analysis (BDA) for deciding what sensing actions should be performed. This ooers a probabilistic framework that provides a more dynamic and modular behaviour than traditional rule based planners. Experiments show that the B...

Bayesian wavelet shrinkage methods are defined through a prior distribution on the space of wavelet coefficients after a Discrete Wavelet Transformation has been applied to the data. Posterior summaries of the wavelet coefficients establish a Bayes shrinkage rule. After the Bayes shrinkage is performed, an Inverse Discrete Wavelet Transformation can be used to recover the signal that generated ...

Kalai and Lehrer (93a, b) have shown that if players' beliefs about the future evolution of play is absolutely continuous with respect to play induced by optimal strategies then Bayesian updating eventually leads to Nash equilibrium. In this paper, we present the ̄rst set of necessary and su±cient conditions that ensure that Bayesian updating eventually leads to Nash equilibrium. More important...

Humans and other animals behave as if we perform fast Bayesian inference underlying decisions and movement control given uncertain sense data. Here we show that a biophysically realistic model of the subthreshold membrane potential of a single neuron can exactly compute the numerator in Bayes rule for inferring the Poisson parameter of a sensory spike train. A simple network of spiking neurons ...

The analysis of nominal data is often reduced to accumulation and description. Bayesian methods offer a possibility to analyse nominal data in a more sophisticated way. The possibility to indicate a structure via graphical representation, where variables are nodes and relationships are edges, enriches this method and makes it a powerful tool for data analysis. In this paper, an overview on Baye...

We present Bayesian updating of an imprecise probability measure, represented by a class of precise multidimensional probability measures. Choice and analysis of our class are motivated by expert interviews that we conducted with modelers in the context of climatic change. From the interviews we deduce that generically, experts hold a much more informed opinion on the marginals of uncertain par...

Probability updating via Bayes' rule often entails extensive informational and computational requirements. In consequence, relatively few practical applications of Bayesian adaptive control techniques have been attempted. This paper discusses an alternative approach to adaptive control, Bayesian in spirit, which shifts attention from the updating of probability distributions via transitional pr...

Maintaining semantics for uncertainty is critical during knowledge acquisition. We examine Bayesian KnowledgeBases (BKBs) which are a generalization of Bayesian networks. BKBs provide a highly flexible and intuitive representation following a basic “if-then” structure in conjunction with probability theory. We present theoretical results concerning BKBs and how BKBs naturally and implicitly pre...