AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Neuronal Gaussian Process Regression

Johannes Friedrich

NeurIPS 2020 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: PAC-Bayes and decoupled GP learning · 0 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
BioNN (sparse GP-style network with local rules) vs VFEBioNN · Boston Housingpredictive log likelihood: -2.483 -> -2.605Hurt
BioNN vs VFEBioNN · Energy Efficiencypredictive log likelihood: -0.712 -> -0.729No clear effect
BioNN vs VFEBioNN · Kin8nmpredictive log likelihood: 0.972 -> 1.031Improved
BioNN vs VFEBioNN · Naval Propulsionpredictive log likelihood: 8.800 -> 9.059Improved
Replace VFE weights with ANN weights trained by Adam (NLL loss, 40 passes) from GP initializationsparse GP network · Naval Propulsionpredictive log likelihood: 8.800 -> 9.171Improved
ANN vs MC Dropout and PBPANN · UCI datasetspredictive log likelihoodImproved
BioNN vs FITC approximation to full GPBioNN · Concrete StrengthKL(p||q): 69,425.31 -> 29.71Improved
BioNN vs VFE approximation to full GPBioNN · Boston HousingKL(p||q): 15.37 -> 29.05Hurt
BioNN vs VFE approximation to full GPBioNN · Energy EfficiencyKL(p||q): 4.79 -> 5.24No clear effect
Increase number of inducing points/neurons to an unnecessarily large number (ablation)BioNN · SnelsonNLPDHurt
Learn noise level from output y in network instead of VFE/FITC predictive varianceBioNN · Snelson, varied noisenoise variance estimate / NLPDImproved
Optimize tuning curve centers (and widths) with REINFORCEBioNN · Snelsontest RMSE / NLPDImproved

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