Goto

Collaborating Authors

 Barcelona Province



Discriminative Gaifman Models

Mathias Niepert

Neural Information Processing Systems

Considering local and bounded-size neighborhoods of knowledge bases renders logical inference and learning tractable, mitigates the problem of overfitting, and facilitates weight sharing.




Learning Sparse Gaussian Graphical Models with Overlapping Blocks

Seyed Mohammad Javad Hosseini, Su-In Lee

Neural Information Processing Systems

Second, GRAB blocks (Figa priorioruseasequential fixed. Thefirsttwo terms,logdet ( ) trace (S ), in Eq (3) correspondtologP(X| ), thelog-likelihoodof GGM givenaparticularparameter (i.e., anestimateof 1), asdescribedin Section 2.1.



BackpropKF: LearningDiscriminativeDeterministic StateEstimators

Neural Information Processing Systems

Generative state estimators based on probabilistic filters and smoothers are one of the most popular classes of state estimators for robots and autonomous vehicles.