Results 11  20
of
20,964
The prototypical Restricted Boltzmann Machine
"... We introduce the spike and slab Restricted Boltzmann Machine, characterized by having both a realvalued vector, the slab, and a binary variable, the spike, associated with each unit in the hidden layer. The model possesses some practical properties such as being amenable to Block Gibbs sampling as ..."
Abstract
 Add to MetaCart
We introduce the spike and slab Restricted Boltzmann Machine, characterized by having both a realvalued vector, the slab, and a binary variable, the spike, associated with each unit in the hidden layer. The model possesses some practical properties such as being amenable to Block Gibbs sampling
The Nonnegative Boltzmann Machine
, 2000
"... The nonnegative Boltzmann machine (NNBM) is a recurrent neural network model that can describe multimodal nonnegative data. Application of maximum likelihood estimation to this model gives a learning rule that is analogous to the binary Boltzmann machine. We examine the utility of the mean field ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
The nonnegative Boltzmann machine (NNBM) is a recurrent neural network model that can describe multimodal nonnegative data. Application of maximum likelihood estimation to this model gives a learning rule that is analogous to the binary Boltzmann machine. We examine the utility of the mean
Discrete restricted Boltzmann machines
, 2015
"... We describe discrete restricted Boltzmann machines: probabilistic graphical models with bipartite interactions between visible and hidden discrete variables. Examples are binary restricted Boltzmann machines and discrete näıve Bayes models. We detail the inference functions and distributed represen ..."
Abstract

Cited by 15 (3 self)
 Add to MetaCart
We describe discrete restricted Boltzmann machines: probabilistic graphical models with bipartite interactions between visible and hidden discrete variables. Examples are binary restricted Boltzmann machines and discrete näıve Bayes models. We detail the inference functions and distributed
Transformation Equivariant Boltzmann Machines
"... Abstract. We develop a novel modeling framework for Boltzmann machines, augmenting each hidden unit with a latent transformation assignment variable which describes the selection of the transformed view of the canonical connection weights associated with the unit. This enables the inferences of the ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
Abstract. We develop a novel modeling framework for Boltzmann machines, augmenting each hidden unit with a latent transformation assignment variable which describes the selection of the transformed view of the canonical connection weights associated with the unit. This enables the inferences
Subspace Restricted Boltzmann Machine
"... The subspace Restricted Boltzmann Machine (subspaceRBM) is a thirdorder Boltzmann machine where multiplicative interactions are between one visible and two hidden units. There are two kinds of hidden units, namely, gate units and subspace units. The subspace units reflect variations of a pattern in ..."
Abstract
 Add to MetaCart
The subspace Restricted Boltzmann Machine (subspaceRBM) is a thirdorder Boltzmann machine where multiplicative interactions are between one visible and two hidden units. There are two kinds of hidden units, namely, gate units and subspace units. The subspace units reflect variations of a pattern
The Nonnegative Boltzmann Machine
"... Abstract The nonnegative Boltzmann machine (NNBM) is a recurrent neural network model that can describe multimodal nonnegative data. Application of maximum likelihood estimation to this model gives a learning rule thatis analogous to the binary Boltzmann machine. We examine the utility of the mean ..."
Abstract
 Add to MetaCart
Abstract The nonnegative Boltzmann machine (NNBM) is a recurrent neural network model that can describe multimodal nonnegative data. Application of maximum likelihood estimation to this model gives a learning rule thatis analogous to the binary Boltzmann machine. We examine the utility of the mean
by Migrating Boltzmann Machines
, 1992
"... An efficient execution of parallel programs on parallel computers needs a support from static or dynamic allocation algorithms. The aim of an allocation algorithm is to perform mapping, i.e. an optimal placement of communicating processes into an architecture of a parallel target machine. This mappi ..."
Abstract
 Add to MetaCart
. This mapping problem belongs to a class of combinatorial problems and i ~ known as NPcomplete. In this report a solution based on migrating Boltzmann Machines is proposed. This solution, based on migrating Boltzmann Machines(MBM) combines two methods: the first one is a game theoretical approach [3
Categorical Boltzmann Machines
, 1998
"... This paper presents a mathematical derivation of a generalization of the Boltzmann Machine capable of modeling categorical (1 of n) random variables. 1 Introduction The Boltzmann machine [6] is a method of representing a joint probability distribution over a set of random variables using a symmetri ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
This paper presents a mathematical derivation of a generalization of the Boltzmann Machine capable of modeling categorical (1 of n) random variables. 1 Introduction The Boltzmann machine [6] is a method of representing a joint probability distribution over a set of random variables using a
Unsupervised Learning for Boltzmann Machines
"... An unsupervised learning algorithm for a stochastic recurrent neural network based on the Boltzmann Machine architecture is formulated in this paper. The maximization of the Mutual Information between the stochastic output neurons and the clamped inputs is used as an unsupervised criterion for train ..."
Abstract
 Add to MetaCart
An unsupervised learning algorithm for a stochastic recurrent neural network based on the Boltzmann Machine architecture is formulated in this paper. The maximization of the Mutual Information between the stochastic output neurons and the clamped inputs is used as an unsupervised criterion
Multiple Texture Boltzmann Machines
"... We assess the generative power of the mPoTmodel of [10] with tiledconvolutional weight sharing as a model for visual textures by specifically training on this task, evaluating model performance on texture synthesis and inpainting tasks using quantitative metrics. We also analyze the relative import ..."
Abstract

Cited by 10 (0 self)
 Add to MetaCart
importance of the mean and covariance parts of the mPoT model by comparing its performance to those of its subcomponents, tiledconvolutional versions of the PoT/FoE and GaussianBernoulli restricted Boltzmann machine (GBRBM). Our results suggest that while stateoftheart or better performance can
Results 11  20
of
20,964