Michael I. Jordan

TL;DR: This work defines and study an “exchangeable feature probability function” (EFPF)—analogous to the EPPF in the clustering setting—for certain types of feature models, and introduces a “feature paintbox” characterization—analogously to the Kingman paintbox for clustering—of the class of exchangeable feature models.

TL;DR: A neural network architecture was designed that learned to produce neural commands to a set of muscle-like actuators based only on information about spatial errors to generate point-to-point horizontal arm movements and the resulting muscle activation patterns and hand trajectories were found to be similar to those observed experimentally for human subjects.

TL;DR: A simple and scalable algorithm for large-margin estimation of structured models, including an important class of Markov networks and combinatorial models, with linear convergence using simple gradient and projection calculations is presented.

TL;DR: GimVI, a deep generative model for the integration of spatial transcriptomic data and scRNA-seq data that can be used to impute missing genes, is proposed and compared to alternative methods from computational biology or domain adaptation on real datasets.

TL;DR: A formal probabilistic framework for combining phylogenetic shadowing with feature-based functional annotation methods is developed and a generalized hidden Markov phylogeny (GHMP) is shown how GHMPs can be used to predict complete shared gene structures in multiple primate sequences.