Learning in restricted Boltzmann machine is typically hard due to the computation of gradients of log-likelihood function. To describe the network state statistics of the restricted Boltzmann machine, we develop an advanced mean field theory based on the Bethe approximation. Our theory provides an efficient message passing based method that evaluates not only the partition function (free energy...

Boltzmann machine and new activation function are examined for its ability to accelerate the performance of doing logic programming in Hopfield neural network. Boltzmann machine has a higher capacity than the new activation function. This learning rule also suffers significantly less capacity loss as the network gets larger and more complex. Comparisons are made between these rules to see which...

Much work has been done refining and characterizing the receptive fields learned by deep learning algorithms. A lot of this work has focused on the development of Gabor-like filters learned when enforcing sparsity constraints on a natural image dataset. Little work however has investigated how these filters might expand to the temporal domain, namely through training on natural movies. Here we ...

Training a Boltzmann machine with hidden units is appropriately treated in information geometry using the information divergence and the technique of alternating minimization. The resulting algorithm is shown to be closely related to gradient descent Boltzmann machine learning rules, and the close relationship of both to the EM algorithm is described. An iterative proportional fitting procedure...

Learning in restricted Boltzmann machine is typically hard due to the computation of gradients of log-likelihood function. To describe the network state statistics of the restricted Boltzmann machine, we develop an advanced mean-field theory based on the Bethe approximation. Our theory provides an efficient message-passing-based method that evaluates not only the partition function (free energy...

We consider the problem of learning Boltzmann machine classifiers from relational data. Our goal is to extend the deep belief framework of RBMs to statistical relational models. This allows one to exploit the feature hierarchies and the non-linearity inherent in RBMs over the rich representations used in statistical relational learning (SRL). Specifically, we use lifted random walks to generate...

In this study, a novel machine learning algorithm, restricted Boltzmann machine (RBM), is introduced. The algorithm is applied for the spectral classification in astronomy. RBM is a bipartite generative graphical model with two separate layers (one visible layer and one hidden layer), which can extract higher level features to represent the original data. Despite generative, RBM can be used for...

Proper cloud segmentation can serve as an important precursor to predicting the output of solar power plants. However, due to the high variability of cloud appearance, and the high dynamic range between different sky regions, cloud segmentation is a surprisingly difficult task. In this paper, we present an approach to cloud segmentation and classification that is based on representation learnin...

Speaker verification is the task of determining whether two utterances represent the same person. After representing the utterances in the i-vector space, the crucial problem is only how to compute the similarity of two i-vectors. Metric learning has provided a viable solution to this problem. Until now, many metric learning algorithms have been proposed, but they are usually limited to learnin...

An artificial neural network, such as a Boltzmann machine, can be trained with the Hebb rule so that it stores static patterns and retrieves a particular pattern when an associated cue is presented to it. Such a network, however, cannot effectively deal with dynamic patterns in the manner of living creatures. Here, we design a dynamic Boltzmann machine (DyBM) and a learning rule that has some o...