Restricted Boltzmann Machines
PulseAugur coverage of Restricted Boltzmann Machines — every cluster mentioning Restricted Boltzmann Machines across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Quantum Annealing vs. Gibbs Sampling for RBMs: New Research
A new research paper compares the effectiveness of D-Wave's quantum annealing technology against the Gibbs Monte Carlo method for sampling probability distributions in Restricted Boltzmann Machines (RBMs). The study fou…
-
New kernel enhances Restricted Boltzmann Machine learning efficiency
Researchers have developed a novel nonlocal transition kernel designed to improve the efficiency and stability of learning Restricted Boltzmann Machines (RBMs). This new kernel addresses the limitations of traditional b…
-
AI model learns Bach's music, reveals limitations in structure encoding
Researchers have explored how Restricted Boltzmann Machines (RBMs), a type of energy-based model, encode musical structures. By training an RBM on symbolic music from J.S. Bach, converted into a piano-roll format, the s…
-
New Parallel Trajectory Tempering algorithm enhances Energy-Based Model training
Researchers have developed a new training algorithm called Parallel Trajectory Tempering (PTT) for Energy-Based Models (EBMs). This method addresses the issue of poor Markov Chain Monte Carlo mixing, which often hinders…
-
Machine learning enhances quantum simulations for complex biological systems
Researchers have developed a novel machine-learned approach, QSCI-RBM, to generate compact subspaces for quantum selected configuration interaction (QSCI) within the density matrix embedding theory (DMET) framework. Thi…
-
New method improves RBMs for out-of-distribution data rejection
Researchers have developed a new method to improve the performance of Restricted Boltzmann Machines (RBMs) when dealing with out-of-distribution (OOD) inputs. By training RBMs with auxiliary random binary images assigne…
-
Statistical mechanics used to explain machine learning and memorization
This thesis explores the theoretical underpinnings of machine learning and artificial neural networks using tools from statistical mechanics. It aims to improve understanding of how these systems learn and memorize data…
-
New research explores activation functions in Restricted Boltzmann Machines
Researchers have explored the statistical properties of weights and hidden unit nonlinearities in Restricted Boltzmann Machines (RBMs). The study focused on four activation functions: Linear, Step, ReLU, and Exponential…
-
New bounds shown for restricted Boltzmann machine sampling
Researchers have demonstrated new mixing time bounds for the alternating-scan sampler applied to positively weighted restricted Boltzmann machines. The analysis, which leverages techniques from Markov chain theory and G…
-
Researchers explore nonequilibrium dynamics to enhance unsupervised generative models
Researchers have demonstrated that nonequilibrium dynamics can enhance unsupervised generative modeling by inducing latent-state cycles. Their model, which uses visible and hidden variables with distinct transition matr…