AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Removing Inter-Experimental Variability from Functional Data in Systems Neuroscience

Dominic Gonschorek, Larissa Höfling, Klaudia P. Szatko, Katrin Franke, Timm Schubert, Benjamin Adric Dunn, Philipp Berens, David A. Klindt, Thomas Euler

NeurIPS 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 10 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
adversarial domain-removal (RAVE) instead of raw datacell type classifier · Bipolar cells A/Bdomain classifier accuracy: 99.8 (0.1) -> 77.5 (0.5)Improved
add cell type supervision to adversarial method (RAVE+ vs RAVE)RAVE · Bipolar cells A/BARI domain: 28.9 (1.2) -> 10.0 (1.2)Improved
add cell type supervision to adversarial method (RAVE+ vs RAVE)RAVE · Bipolar cells A/Bcell type classifier accuracy: 69.5 (0.4) -> 78.6 (0.8)Improved
use RAVE instead of scGen/Harmony/Linearcell type transfer · Bipolar cells A/BARI type: 14.3 (2.6) -> 81.2 (2.7)Improved
use RAVE instead of scGencell type classifier · Bipolar cells A/Bcell type classifier accuracy: 84.7 (0.8) -> 69.5 (0.4)Hurt
use RAVE+ instead of raw data for cell type predictioncell type classifier · Dataset B depth score (all)Jensen-Shannon distance: 31 -> 17Improved
use RAVE reconstructions instead of rawdownstream correlation analysis · Dataset Bcorrelation difference local vs full-fieldImproved

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