Infinite Dynamic Bayesian Networks
Finale Doshi, David Wingate, Josh Tenenbaum, Nicholas Roy · DSpace@MIT (Massachusetts Institute of Technology) · 2011
We present the infinite dynamic Bayesian network model (iDBN), a nonparametric, factored state-space model that generalizes dynamic Bayesian networks (DBNs). The iDBN can infer every aspect of a DBN: the number of hidden factors, the number of values each factor can take, and (arbitrarily complex) connections and conditionals between factors and observations. In this way, the iDBN generalizes other nonparametric statespacemodels, whichuntilnowgenerally focused on binary hidden nodes and more restricted connection structures. We show how this new prior allows us to find interesting structureinbenchmarktestsandontworealworld datasets involving weather data and neural information flow networks. 1.