One potential strength of recurrent neural networks (RNNs) is their – theoretical – ability to find a connection between cause and consequence in time series in an constraint-...
A new model for learning from multinomial data has recently been developed, giving predictive inferences in the form of lower and upper probabilities for a future observation. Apa...
As richer models for stereo vision are constructed, there is a growing interest in learning model parameters. To estimate parameters in Markov Random Field (MRF) based stereo formu...
Many kernel learning methods have to assume parametric forms for the target kernel functions, which significantly limits the capability of kernels in fitting diverse patterns. Som...
Tree-structured probabilistic models admit simple, fast inference. However, they are not well suited to phenomena such as occlusion, where multiple components of an object may dis...