AI Paper Atlas

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

Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel

Xin Qiu, Elliot Meyerson, Risto Miikkulainen

ICLR 2020 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Single-model predictive uncertainty · 12 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
apply RIO residual estimation with an I/O kernel to a pretrained NNstandard NN regressors · 12 real-world regression datasetsRMSEImproved
apply RIO to a pretrained DenseNet age estimatorDenseNet · IMDB Age EstimationMAE: 7.43 -> 6.35Improved
add residual estimation to direct outcome fitting (ablation)RIO variants · 12 real-world regression datasetsRMSEImproved
add the I/O kernel rather than using input-only or output-only kernels (ablation)RIO variants · 12 real-world regression datasetsRMSEImproved
use residual estimation with input kernel only instead of full RIO (ablation)RIO · yachtRMSE: 1.46±0.49 -> 2.03±0.73Hurt
use residual estimation with output kernel only instead of full RIO (ablation)RIO · yachtRMSE: 1.46±0.49 -> 1.88±0.66Hurt
estimate outcomes directly with an output-only kernel instead of full RIO (ablation)RIO · yachtRMSE: 1.46±0.49 -> 1.86±0.64Hurt
estimate outcomes directly with the I/O kernel instead of fitting residuals (ablation)RIO · yachtRMSE: 1.46±0.49 -> 1.58±0.52Mixed
use residual estimation with input kernel only instead of full RIO (ablation)RIO · ENB/hRMSE: 0.70±0.38 -> 0.79±0.46Hurt
use residual estimation with output kernel only instead of full RIO (ablation)RIO · ENB/hRMSE: 0.70±0.38 -> 0.80±0.43Hurt
estimate outcomes directly with output-only kernel instead of full RIO (ablation)RIO · ENB/hRMSE: 0.70±0.38 -> 0.88±0.48Hurt
estimate outcomes directly with the I/O kernel instead of fitting residuals (ablation)RIO · ENB/hRMSE: 0.70±0.38 -> 0.76±0.41Hurt

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