AI Paper Atlas

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

Learning Non-Linear Dynamics of Decision Boundaries for Maintaining Classification Performance

Atsutoshi Kumagai, Tomoharu Iwata

AAAI 2017 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Bayesian view of meta-learning · 5 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
Model dynamics of each classifier parameter with a Gaussian process instead of linear autoregression (AAAI16)future-classifier model · LinearAUC: 0.940 -> 0.988Improved
Use GP dynamics instead of vector autoregressionfuture-classifier model · Non-linearAUC: 0.952 -> 0.984Improved
Use GP dynamics instead of vector autoregressionfuture-classifier model · SPAM2AUC: 0.907 -> 0.956Improved
Use GP dynamics instead of vector autoregressionfuture-classifier model · ELEC2AUC: 0.926 -> 0.921Hurt
Use GP dynamics instead of vector autoregressionfuture-classifier model · ONPAUC: 0.533 -> 0.705Improved
Use GP dynamics instead of vector autoregressionfuture-classifier model · BLOGAUC: 0.827 -> 0.838Improved
Predict future classifier vs. batch logistic regression trained on all datafuture-classifier model · Non-linearAUC: 0.302 -> 0.984Improved
Predict future classifier vs. present-only classifierfuture-classifier model · BLOGAUC: 0.754 -> 0.838Improved
Predict future classifier vs. online logistic regressionfuture-classifier model · BLOGAUC: 0.730 -> 0.838Improved
Vary the number of training data per time unitfuture-classifier model · SPAM2AUCNo 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