A good model of object shape is essential in applications such as segmentation, object detection, inpainting and graphics. For example, when performing segmentation, local constra...
While Boltzmann Machines have been successful at unsupervised learning and density modeling of images and speech data, they can be very sensitive to noise in the data. In this pap...
Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hi...
The deep Boltzmann machine is a powerful model that extracts the hierarchical structure of observed data. While inference is typically slow due to its undirected nature, we argue ...
We assess the generative power of the mPoTmodel of [10] with tiled-convolutional weight sharing as a model for visual textures by specifically training on this task, evaluating m...
A common approach in machine learning is to use a large amount of labeled data to train a model. Usually this model can then only be used to classify data in the same feature spac...
Abstract. The resolution of combinatorial optimization problems can greatly benefit from the parallel and distributed processing which is characteristic of neural network paradigm...
We present a method for mapping a given Bayesian network to a Boltzmann machine architecture, in the sense that the the updating process of the resulting Boltzmann machine model pr...
We present a mixture model whose components are Restricted Boltzmann Machines (RBMs). This possibility has not been considered before because computing the partition function of a...