My paper in the Journal of Internet Medical Research about discussion of electronic cigarettes on Twitter.
Summary of my work developing a high-performance Python library for inference of nonparametric Latent Dirichlet Allocation.
Code for drawing samples from the distribution of tables created by a Chinese restaurant process after n patrons are seated.
Derivation of a collapsed Gibbs sampler for a finite mixture model with a uniform Dirichlet prior, and extension to the Dirichlet Process Mixture Model.
A discussion of the confusing and sometimes contradictory use of the term 'Dirichlet process' in the nonparametric Bayesian literature.
Applying nonparametric latent Dirichlet allocation to discover topics in Econtalk podcast transcripts using a hierarchical Dirichlet process.
Notes on applying the equations from the Hierarchical Dirichlet Process paper to nonparametric Latent Dirichlet Allocation.
Derivation of a full Gibbs sampler for a finite mixture model with a uniform Dirichlet prior, as a step toward the Dirichlet Process Mixture Model.
