Frank Wood
fwood @ cs <dot> brown <dot> edu -- (401) 351-4222 Skype MeT!

Hypergeometric Functions
Matlab contains a Hypergeometric1F1 function named hypergeom which unfortunately calls underlying maple symbolic routines instead of numerically approximating the function value by truncating the series as I do in these matlab scripts: Hypergeometric1F1.m Hypergeometric1F1Regularized.m
Infinite Gaussian Mixture Modeling
Infinite mixture modeling (also known as Dirichlet process mixture modeling) is being applied with success in a number of domains including document modeling, 3-d scene reconstruction, and so forth. Following on Rasmussen's NIPS 2000 paper, The Infinite Gaussian Mixture Model, I implemented the multivariate Gaussian infinite mixture model and an MCMC sampler to learn model parameters given data. In my 2006 EMBS submission, A non-parametric bayesian approach to spike sorting PDF, I applied this code to the problem of spike sorting. This is a generic Chinese Restaurant Process hybrid Gibbs/Metropolis sampler implementation of infinite Gaussian mixture modeling, with a simple example application. .zip
Mixed Discrete-Continuous Particle Filter Estimation
This code forms the basis for my EMBS 2005 submission entitled Inferring attentional state and kinematics from motor cortical firing rates .pdf. In this work a mixed continuous (monkey hand state) and discrete (attentional state) model is defined and a particle filter is used to recursively estimate both simultaneously from firing rates from the same motor cortical population. .zip