G. D'Agostini - Probability and Statistics
... thinking and tinkering
- JavaBayes is a system that handles Bayesian networks:
it calculates marginal probabilities and expectations,
produces explanations, performs robustness analysis,
and allows the user to import, create, modify and export networks.
Implemented in Java.
- Bayesian inference Using Gibbs Sampling is a piece of computer
software for the Bayesian analysis of complex statistical models
using Markov chain Monte Carlo (MCMC) methods.
Net Toolbox for Matlab
- BNT supports exact and approximate inference, parameter and
static and dynamic (temporal) Bayesian networks, many kinds of probability
distributions (multinomial, Gaussian, noisy-or), etc. It provides a unified
toolbox which can handle (hierarchical) mixtures of experts,
mixtures of Gaussians,
naive Bayes classifiers, HMMs, coupled HMMs, factorial HMMs,
Kalman filters, Markov Random Fields, etc.
- The goal is to discuss the development of an open source library for
probabilstic graphical models.
- A project, started by Lauritzen et al.,
to implement an open source graphical models library in R.
Back to G.D'Agostini Home Page