AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Gaussian Gated Linear Networks

David Budden, Adam Marblestone, Eren Sezener, Tor Lattimore, Gregory Wayne, Joel Veness

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 8 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
Use G-GLN instead of DOUCI regression · Boston Housingtest RMSE: 2.97 -> 2.84Improved
Use G-GLN instead of DOUCI regression · Concrete Compression Strengthtest RMSE: 5.23 -> 5.84Hurt
Use G-GLN instead of DOUCI regression · Energy Efficiencytest RMSE: 1.66 -> 1.31Improved
Use G-GLN instead of PBPUCI regression · Kin8nmtest RMSE: 0.10 -> 0.09Improved
Use G-GLN instead of VIUCI regression · Naval Propulsiontest RMSE: 0.01 -> 0.00Improved
Use G-GLN instead of DOUCI regression · Combined Cycle Power Planttest RMSE: 4.02 -> 3.90Improved
Use G-GLN instead of DOUCI regression · Protein Structuretest RMSE: 4.36 -> 3.77Improved
Use G-GLN instead of DOUCI regression · Wine Quality Redtest RMSE: 0.62 -> 0.57Improved
Use G-GLN instead of PBPUCI regression · Yacht Hydrodynamicstest RMSE: 1.01 -> 3.76Hurt
Use G-GLN instead of TabNet-LSARCOS inverse dynamics · SARCOS inverse dynamicstest MSE: 0.14 -> 0.10Improved
Use G-GLN instead of LinFullPostcontinuous-reward contextual bandits · Financial contextual banditcumulative reward: 3122±1 -> 3018±3Hurt
Use G-GLN instead of BootRMScontinuous-reward contextual bandits · Jester contextual banditcumulative reward: 3269±4 -> 3301±4Improved

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