To support more effective searches in large-scale weaklytagged image collections, we have developed a novel algorithm to integrate both the visual similarity contexts between the...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are the most general conditions under...
There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images re...
Honglak Lee, Roger Grosse, Rajesh Ranganath, Andre...
Abstract. Switching linear dynamic systems (SLDS) attempt to describe a complex nonlinear dynamic system with a succession of linear models indexed by a switching variable. Unfortu...