AI Paper Atlas

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

Autoinverse: Uncertainty Aware Inversion of Neural Networks

Navid Ansari, Hans-peter Seidel, Nima Vahidi Ferdowsi, Vahid Babaei

NeurIPS 2022 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 3 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 uncertainty-aware term (UANA) to NANA · multi-joint robotNFP error: 3.24 \pm 0.51 -> 3.21 \pm 1.48Improved
Add uncertainty-aware term to tandem (UA-tandem)tandem · multi-joint robotNFP error: 4.42 \pm 1.56 -> 4.04 \pm 0.38Improved
Add uncertainty-aware term (UANA) to NANA · multi-joint robotsurrogate error: 1.99 \pm 0.05 -> 9.13 \pm 6.08Hurt
Use ensemble of networks in NA (NA ensemble) without uncertainty term (ablation)NA · multi-joint robotNFP error: 1.17 \pm 0.32Mixed
Use only ReLU activations in the ensemble instead of diverse activations (ablation)UANA · spectral printer, sparse LC datacount of LC>=0.4 solutions: 0 \pm 0 -> 19 \pm 4Hurt
Use UANA instead of NA on data with sparse LC channelNA · spectral printer, sparse datacount of LC>=0.4 solutions: 1604 \pm 11 -> 0 \pm 0Improved
Use UANA instead of NA on data with noisy LC channelNA · spectral printer, noisy datacount of LC>=0.4 solutions: 1029 \pm 23 -> 0 \pm 0Improved
Use UA-tandem instead of tandem on sparse LC datatandem · spectral printer, sparse datacount of LC>=0.4 solutions: 52 \pm 30 -> 0 \pm 0Improved
Use UANA instead of NA on NFP error with standard dataNA · spectral printer, standard dataNFP error: 1.57 \pm 0.001 -> 6.30 \pm 0.031Improved
Add boundary loss regularization to NANA · spectral printerink density distributionMixed
Add smoothness regularization to NANA · soft robotdesign plausibilityImproved
Use UANA without any regularization instead of regularized NANA with smoothness term · soft robotdesign plausibilityNo clear effect

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