BayesFusion has released PySMILE, a SMILE wrapper for direct use from Python. We supported Python in the past but only through jSMILE, SMILE’s Java wrapper. We strive to ensure feature symmetry between the wrappers — features available in one wrapper are generally available in other wrappers and are all described in one wrapper manual.
SMILE 1.2.1 has been released (including jSMILE and SMILE.NET wrappers). This version of SMILE offers performance improvements and bug fixes.
SMILE 1.2.0 has been released (including jSMILE and SMILE.NET wrappers). This version of SMILE includes hybrid modeling functionality, which is available in GeNIe 2.2 since August 2017.
BayesFusion, LLC, has released GeNIe 2.2 with hybrid Bayesian networks capability. Hybrid Bayesian networks allow for both discrete and continuous nodes. GeNIe 2.2 allows for full modeling freedom with no restrictions on the functional form of the interactions between variables and on the probability distributions involved in these interactions.
BayesFusion, LLC, releases SMILE.COM, a SMILE wrapper for use in Microsoft Excel and other OLE Automation/scripting environments.
Prof. Druzdzel, a co-founder of BayesFusion, LLC, gave a presentation on the topic of Learning Bayesian Networks and Causal Discovery at the PyData Warsaw meeting #9: Deep & Machine Learning on 29 March 2017. A recording of the presentation is available through BayesFusion’s YouTube channel (https://youtu.be/UWvxeOo91Fo).
Prof. Druzdzel, a co-founder of BayesFusion, LLC, delivered an invited plenary talk at the Eighth Annual Conference of the Australasian Bayesian Network Modelling Society (ABNMS2016) held at the University of Western Australia on 22-25th November 2016. The conference is an annual meeting of the Australasian Bayesian Network Modelling Society (ABNMS, http://www.abnms.org/). ABNMS’s purpose is to promote the understanding and use of Bayesian network models in scientific, industrial, and research applications. The invited plenary talk, titled “(The Importance of) Human Interface to Bayesian Networks” focused on various user interface techniques employed in GeNIe that compose its widely known user interface. A recording of the talk is available through BayesFusion’s YouTube channel (https://youtu.be/mxeiJbo8FWw).
BayesFusion releases a 64-bit version of the GeNIe Modeler. SMILE has been available in 64-bit version for a while.
Prof. Druzdzel, one of the co-founders of BayesFusion, LLC, participated in the Eighth International Conference on Probabilistic Graphical Models (PGM), which took place in Lugano, Switzerland, September 6-9, 2016. PGM is a biennial meeting that brings together researchers interested in all aspects of graphical models for probabilistic reasoning, decision making, and learning. Prof. Druzdzel took part in a round-table panel “Probabilistic graphical models, software tools, and their applications to real-world problems.” The panel, whose members included representatives of leading software companies in the field, focused on issues related to practical application of probabilistic graphical models.
BayesFusion, LLC, releases an up-to-date documentation and on-line help for GeNIe Modeler. The help document is integrated with GeNIe and also available in PDF and HTML formats.