AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Unsupervised Learning with Truncated Gaussian Graphical Models

Qinliang Su, Xuejun Liao, Chunyuan Li, Zhe Gan, Lawrence Carin

AAAI 2017 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Latent variable marginalization and estimators · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add truncated hidden variables to the bipartite GGM (ablation)RTGGM · MNIST testtest log-prob.: -90.2 -> -83.2Improved
Add truncated hidden variables to the bipartite GGM (ablation)RTGGM · Caltech 101 Silhouettes testtest log-prob.: -350.9 -> -105.1Improved
Use RTGGM instead of RBM500-hidden-node models · MNIST testtest log-prob.: -86.3 -> -83.2Improved
Use RTGGM instead of RBM500-hidden-node models · Caltech 101 Silhouettes testtest log-prob.: -107.7 -> -105.1Improved
Use RTGGM instead of RSM50-topic count models · 20news testperplexity per word: 953 -> 915Improved
Use RTGGM instead of RSM50-topic count models · Reuters testperplexity per word: 988 -> 934Improved
Pretrain the ReLU network with deep RTGGM instead of rectified-RBM1000-1000-1000 ReLU neural network · MNISTclassification error: 1.33% -> 1.17%Improved
Pretrain the ReLU network with deep RTGGM instead of rectified-RBM1000-1000-1000 ReLU neural network · NORBclassification error: 16.43% -> 16.12%Improved
Pretrain the ReLU network with deep RTGGM instead of no pre-training1000-1000-1000 ReLU neural network · MNISTclassification error: 1.43% -> 1.17%Improved
Pretrain the ReLU network with deep RTGGM instead of no pre-training1000-1000-1000 ReLU neural network · NORBclassification error: 16.88% -> 16.12%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy