/ Lawrence Murray

LibBi released

After four years of development, LibBi is now available as open source software. LibBi is used for state-space modelling and Bayesian inference on high-performance computer hardware, including multi-core CPUs, many-core GPUs (graphics processing units) and distributed-memory clusters.

The staple methods of LibBi are based on sequential Monte Carlo (SMC), also known as particle filtering. These methods include particle Markov chain Monte Carlo (PMCMC) and SMC2. Other methods include the extended Kalman filter and some parameter optimisation routines.

LibBi consists of a C++ template library, as well as a parser and compiler, written in Perl, for its own modelling language.

Find out more on the external LibBi site. A good place to start, as a user, is this introductory paper. If you are interested in getting involved in development of the software, please get in touch.

Posted by Lawrence on 23 Jun 2013 in research and software.


Tintii Photoshop plugin tutorial 14 Oct 2009 Red Umbrellas on Rose Street

A Brief Introduction to Urban Lightscape 26 Mar 2012 Looking at the promotional screenshots for [Urban Lightscape][1], the astute, well-travelled and Vietnamese will have no trouble guessing where I’ve been most recently. As I develop some of the photos from the trip, I thought it an opportune time to share some of the ways I’m putting Urban Lightscape to use in my own workflow, and provide a few tips for getting the most out of it.

Tintii 2.5.2 released for all platforms 21 Apr 2011 Tintii 2.5.2 has been released for Windows, Mac and Linux. This release brings the additional features added for Mac in the recent [2.5.1 release][1] to the other platforms, as well as to the Photoshop plugin.

5 Tips to using the Urban Lightscape Photoshop plugin 22 Apr 2012 Leap ahead with these five quick tips for using the [Urban Lightscape Photoshop plugin][1] to correct exposure and balance lighting in your pictures.