Real-valued random hidden variables can be useful for modelling latent structure that explains correlations among observed variables. I propose a simple unit that adds zero-mean G...
We present topic-regression multi-modal Latent Dirichlet Allocation (tr-mmLDA), a novel statistical topic model for the task of image and video annotation. At the heart of our new...
We present topic-regression multi-modal Latent Dirichlet Allocation (tr-mmLDA), a novel statistical topic model for the task of image and video annotation. At the heart of our new...
Duangmanee Putthividhya, Hagai Thomas Attias, Srik...
Directed graphical models with one layer of observed random variables and one or more layers of hidden random variables have been the dominant modelling paradigm in many research ...
Energy-based learning (EBL) is a general framework to describe supervised and unsupervised training methods for probabilistic and non-probabilistic factor graphs. An energy-based ...