dysii

dysii 1.3.0 released

Wednesday, March 5th, 2008

Version 1.3.0 of the dysii Dynamic Systems Library is now available. The new release adds a stochastic Runge-Kutta method for stochastic differential systems, and preliminary density and kernel density (KD) tree implementations.

See the updated documentation and VERSION.txt file in the new distribution for more information.

Both a detailed tutorial and installation guide are on the way also, being partially complete. If these will be of use to you, please bug me to get a move on!

dysii 1.2.0 Released

Sunday, December 2nd, 2007

Version 1.2.0 of the dysii Dynamic Systems Library is now available. The new release adds the Auxiliary Particle Filter, a generalised framework for particle filter resampling strategies, and makes a number of optimisations and bug fixes.

Specific changes include:

  • Added auxiliary particle filter.
  • Added generalised resampling strategy framework.
  • Fixed diagonal covariance detection for optimised Gaussian density calculations.
  • Fixed several serialization bugs.
  • Fixed Wiener process variance bug.

See the updated documentation and VERSION.txt file in the new distribution for more information.

Continuous Time Particle Filtering for fMRI

Thursday, November 29th, 2007

I’ve added a draft version of the paper Continuous Time Particle Filtering for fMRI to the research page, to be presented as a poster at NIPS 2007. Note that this version of the paper is not available in the conference pre-proceedings. The work makes use of both the dysii Dynamic Systems Library for distributed/parallel particle filtering and smoothing, and the fmrii fMRI Modelling Library, both available on this site.

dysii 1.1.0 released

Tuesday, October 9th, 2007

Version 1.1.0 of the dysii Dynamic Systems Library is now available. The primary feature of the new release is an overhauled implementation of the parallel particle filter and smoother, with new distributed storage capability. Serialization of distributions is also now available, working towards a more sophisticated framework for data management.

Specific changes include:

  • Overhauled parallel implementations from master-slave to SPMD.
  • Improved particle smoother with further parallelisation.
  • Added distributed storage of mixtures.
  • Added Gaussian mixture distributions.
  • Added serialization of probability distributions.
  • Fixed Wiener process variance bug.

See the updated documentation and VERSION.txt file in the new distribution for more information.


Category feeds