Semi-supervised learning for structured output prediction

Jurica Levatić

Abstract


This article presents a summary of the doctoral dissertation of the author on the topic of semi-supervised learning for predicting structured outputs.

Full Text:

PDF

References


bibitem{Chapelle:book} Chapelle, O., Sch"olkopf, B., Zien, A. (2006). {it Semi-supervised learning}. Cambridge, Massachusetts: MIT Press.

bibitem{Bakir07:book} G. Bak{i}r, T. Hofmann, B. Sch{"o}lkopf, A. Smola, B. Taskar, S. Vishwanathan (2007) {it Predicting structured data}, The MIT Press.

bibitem{Levatic:phd} J. Levati'{c} (2017) {it Semi-supervised learning for structured output prediction}, PhD Thesis, IPS Jov{z}ef Stefan, Ljubljana, Slovenia.

bibitem{Blockeel:phd} H. Blockeel (1998) {it Top-down induction of first order logical decision trees}, PhD Thesis, Katholieke Universiteit Leuven, Belgium.

bibitem{Levatic_kbs:jrnl} J. Levati'{c}, M. Ceci, D. Kocev, S. Dv{z}eroski, (2017) Self-training for multi-target regression with tree ensembles, {it Knowledge-based systems}, 123:41--60

bibitem{Levatic_ins:jrnl} J. Levati'{c}, D. Kocev, M. Ceci, S. Dv{z}eroski, (2018) Semi-supervised trees for multi-target regression, {it Information Sciences}, 450:109--127

bibitem{Levatic_jiis:jrnl} J. Levati'{c}, M. Ceci, D. Kocev, S. Dv{z}eroski, (2017) Semi-supervised classification trees, {it Journal of Intelligent Information Systems}, 49(3):461--486

bibitem{Levatic_eswa:jrnl} J. Levati'{c}, M. Ceci, T. Stepiv{s}nik, S. Dv{z}eroski, D. Kocev, (2020) Semi-supervised regression trees with application to QSAR modelling, {it Expert Systems with Applications}, 158:113569

bibitem{Nikoloski_eswa:jrnl} S. Nikoloski, D. Kocev, J. Levati'{c}, D. P. Wall, S. Dv{z}eroski, (2021) Exploiting partially-labeled data in learning predictive clustering trees for multi-target regression: A case study of water quality assessment in Ireland, {it Ecological Informatics}, 61:101161




DOI: https://doi.org/10.31449/inf.v46i4.4455

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.