AI Paper Atlas

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

A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks

Qinliang Su, xuejun Liao, Lawrence Carin

NeurIPS 2017 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Gradient estimation for discrete variables

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
Learn unit-specific truncation points instead of using the original RBM nonlinearityRBM · MNISTaverage test log-probability: -86.3 -> -82.5Improved
Learn unit-specific truncation points instead of using the original RBM nonlinearityRBM · Caltech101 Silhouettesaverage test log-probability: -109.0 -> -104.3Improved
Use ReLU-type truncation points [0, +∞) rather than sigmoid-type [0, 1] or tanh-type [-1, 1] (ablation)TruG-RBM · MNISTaverage test log-probability: -97.3; -83.2; -124.5Mixed
Use unit-specific learned nonlinearities rather than fixed ReLU-type truncation points (ablation)TruG-TRBM · Bouncing Balltest prediction error: 4.16±0.42 -> 3.66±0.46Improved
Use fixed ReLU-type truncation points rather than tanh-type truncation points (ablation)TruG-TRBM · CMU Motion Capturetest prediction error: 21.8±0.31 vs 7.3±0.21; 14.9±0.29 vs 5.9±0.22Mixed
Learn truncation points instead of fixing them to a standard nonlinearity (ablation)TruG-TGGM · UCI regression datasetsRMSEMixed
Use unit-specific rather than shared learned truncation points (ablation)TruG-TGGM · UCI regression datasetsRMSEMixed

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