AI Paper Atlas

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

Finding the Homology of Decision Boundaries with Active Learning

Weizhi Li, Gautam Dasarathy, Karthikeyan Natesan Ramamurthy, Visar Berisha

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection

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 active querying (7NN graph) instead of passive for classifier selectionPD1-based selection, SVM · Banknotetest error rate: 0.3753 -> 0.0836Improved
use active querying (7NN graph) instead of passivePD1-based selection, neural network · Banknotetest error rate: 0.4316 -> 0.1058Improved
use active querying (7NN graph) instead of passivePD1-based selection, KNN · MNISTtest error rate: 0.0129 -> 0.0104Improved
use active querying (7NN graph) instead of passivePD1-based selection, neural network · MNISTtest error rate: 0.0202 -> 0.0388Hurt
use active querying (7NN graph) instead of passivePD1-based selection, KNN · CIFAR10test error rate: 0.3065 -> 0.3109Hurt
use active querying (7NN graph) instead of passivePD1-based selection, SVM · CIFAR10test error rate: 0.4683 -> 0.4464Improved
use active querying (7NN graph) instead of passivePD1-based selection, decision tree · CIFAR10test error rate: 0.3625 -> 0.3625No clear effect
ensemble topology-selected and validation-selected classifier (active)Active3 · Banknote, neural networktest error rate: 0.1058 -> 0.0072Improved
ensemble topology-selected and validation-selected classifier (passive)Passive · CIFAR10, SVMtest error rate: 0.4683 -> 0.2698Improved
active vs passive within ensemble selectionActive3 (ens) · CIFAR10, KNNtest error rate: 0.2987 -> 0.2935Improved
active vs passive within ensemble selectionActive3 (ens) · CIFAR10, decision treetest error rate: 0.3137 -> 0.3221Hurt
active vs passive within ensemble selectionActive3 (ens) · Banknote, decision treetest error rate: 0.0741 -> 0.0770Hurt

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