Active Learning by Learning

Authors: Wei-Ning Hsu, Hsuan-Tien Lin

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive empirical studies of the resulting ALBL algorithm confirm that it performs better than state-of-the-art strategies and a leading blending algorithm for active learning, all of which are based on human-designed philosophy.
Researcher Affiliation Academia Wei-Ning Hsu Department of Electrical Engineering, National Taiwan University mhng1580@gmail.com Hsuan-Tien Lin Department of Computer Science and Information Engineering, National Taiwan University htlin@csie.ntu.edu.tw
Pseudocode Yes Algorithm 1 ACTIVE LEARNING BY LEARNING
Open Source Code No The paper does not provide any explicit statement or link for the open-source code of the ALBL methodology described.
Open Datasets Yes We take six real-world data sets, liver, sonar, vehicle, breast, diabetes, heart) from the UCI Repository (Bache and Lichman 2013).
Dataset Splits No The paper states 'we reserve 80% of the instances as the training set, and retain the other 20% as the test set,' but does not specify a separate validation dataset split.
Hardware Specification No The paper does not specify any particular hardware (e.g., GPU, CPU models, or memory) used for running the experiments.
Software Dependencies No The paper mentions using 'Lib SVM (Chang and Lin 2011)' but does not provide a specific version number for this or any other software dependency.
Experiment Setup Yes We take SVM (Vapnik 1998) as the underlying classifier and use Lib SVM (Chang and Lin 2011) with all the default parameters to train the classifier.