REVIEW 3 cited by
Gaussian-Bernoulli RBMs Without Tears
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We revisit the challenging problem of training Gaussian-Bernoulli restricted Boltzmann machines (GRBMs), introducing two innovations. We propose a novel Gibbs-Langevin sampling algorithm that outperforms existing methods like Gibbs sampling. We propose a modified contrastive divergence (CD) algorithm so that one can generate images with GRBMs starting from noise. This enables direct comparison of GRBMs with deep generative models, improving evaluation protocols in the RBM literature. Moreover, we show that modified CD and gradient clipping are enough to robustly train GRBMs with large learning rates, thus removing the necessity of various tricks in the literature. Experiments on Gaussian Mixtures, MNIST, FashionMNIST, and CelebA show GRBMs can generate good samples, despite their single-hidden-layer architecture. Our code is released at: \url{https://github.com/lrjconan/GRBM}.
Forward citations
Cited by 3 Pith papers
-
Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering
Parallel Trajectory Tempering with reservoirs and adaptive steps makes equilibrium maximum-likelihood training of EBMs practical and often better than PCD and deep generators on multimodal scientific data.
-
Exploration of the generative capabilities of Boltzmann machines applied to social systems under the majority rule
Deep belief networks with Gaussian visible units can impute missing opinions in a three-state majority-vote model with growing error under noise, and the reconstructed configurations remain classified as critical by a...
-
Fusing Multi- and Hyperspectral Satellite Data for Harmful Algal Bloom Monitoring with Self-Supervised and Hierarchical Deep Learning
SIT-FUSE maps harmful algal bloom concentration and species from fused VIIRS/MODIS/Sentinel-3/PACE/TROPOMI data using self-supervised hierarchical clustering, with limited in-situ validation.
Discussion (0). Sign in to comment.