
 Description:
BayesPy provides tools for variational Bayesian inference in Python. The model is constructed as a Bayesian network. The aim is to provide a tool which is efficient, flexible and extendable enough for expert use but also accessible for more casual users.
Documentation: http://bayespy.org
Repository: https://github.com/bayespy/bayespy
 Changes to previous version:
 Fix computation of probability density of Dirichlet nodes
 Use unit tests for all code snippets in docstrings and documentation
 BibTeX Entry: Download
 URL: Project Homepage
 Supported Operating Systems: Platform Independent
 Data Formats: Hdf, Csv
 Tags: Variational Inference, Bayesian Inference
 Archive: download here
Other available revisons

Version Changelog Date 0.4.1  Define extra dependencies needed to build the documentation
November 2, 2015, 13:40:09 0.4.0  Fix Gaussian node sampling
 Implement Add node for Gaussian nodes
 Raise error if attempting to install on Python 2
 Return both relative and absolute errors from numerical gradient checking
 Add nose plugin to filter unit test warnings appropriately
November 2, 2015, 13:02:37 0.3.7  Enable keyword arguments when plotting via the inference engine
 Add initial support for logging
September 23, 2015, 14:29:20 0.3.6  Add maximum likelihood node for the shape parameter of Gamma
 Fix Hinton diagrams for 1D and 0D Gaussians
 Fix autosave interval counter
 Fix bugs in constant nodes
September 23, 2015, 13:13:45 0.3.5  Fix indexing bug in VB optimization (not VBEM)
 Fix demos
June 9, 2015, 13:17:00 0.3.4  Fix computation of probability density of Dirichlet nodes
 Use unit tests for all code snippets in docstrings and documentation
June 9, 2015, 12:54:04 0.3.3  Change license to the MIT license
 Improve SumMultiply efficiency
 Hinton diagrams for gamma variables
 Possible to load only nodes from HDF5 results
June 5, 2015, 16:01:22 0.3.2  Concatenate node added
 Unit tests for plotting fixed
March 16, 2015, 11:58:37 0.3.1  Gaussian mixture 2D plotting improvements
 Covariance matrix sampling improvements
 Minor documentation fixes
March 12, 2015, 14:32:34 0.3  Add gradientbased optimization methods (Riemannian/natural gradient or normal)
 Add collapsed inference
 Add the pattern search method
 Add deterministic annealing
 Add stochastic variational inference
 Add optional input signals to Gaussian Markov chains
 Add unit tests for plotting functions (by Hannu Hartikainen)
 Add printing support to nodes
 Drop Python 3.2 support
March 5, 2015, 09:26:26 0.2.3  Fix matplotlib compatibility broken by recent changes in matplotlib>=1.4.0
 Add random sampling for Binomial and Bernoulli nodes
 Fix minor bugs, for instance, in plot module
December 3, 2014, 14:51:10 0.2.2  Fix normalization of categorical Markov chain probabilities (fixes HMM demo)
 Fix initialization from parameter values
November 1, 2014, 11:06:01 0.2.1 Add workaround for matplotlib 1.4.0 bug related to interactive mode which affected monitoring
Fix bugs in Hinton diagrams for Gaussian variables
September 30, 2014, 16:35:11 0.2 added all common distributions: Poisson, beta, multinomial, Bernoulli, categorical, etc
added Gaussian arrays (not just scalars or vectors)
added Gaussian Markov chains with timevarying or swithing dynamics
added discrete Markov chains (enabling hidden Markov models)
added deterministic gating node
added deterministic general sumproduct node
added parameter expansion
added new plotting functions: pdf, Hinton diagram
added monitoring of posterior distributions during iteration
improved documentation
August 14, 2014, 17:24:22 0.1 Initial Announcement on mloss.org.
September 25, 2013, 16:10:58
Comments
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.