A4 Article in conference proceedings
Sparse minimal learning machine using a diversity measure minimization (2019)


Dias, M. L. D., Sousa, L. S., Rocha Neto, A. R. D., Mattos, C. L. C., Gomes, J. P.P., & Kärkkäinen, T. (2019). Sparse minimal learning machine using a diversity measure minimization. In ESANN 2019 : Proceedings of the 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (pp. 269-274). ESANN. https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-178.pdf


JYU authors or editors


Publication details

All authors or editors: Dias, Madson L. D.; Sousa, Lucas S.; Rocha Neto, Ajalmar R. da; Mattos, César L. C.; Gomes, João P. P.; Kärkkäinen, Tommi

Parent publication: ESANN 2019 : Proceedings of the 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Conference:

  • European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Place and date of conference: Bruges, Belgium, 24.-26.4.2019

ISBN: 978-2-87587-065-0

eISBN: 978-2-87587-066-7

Publication year: 2019

Pages range: 269-274

Number of pages in the book: 696

Publisher: ESANN

Publication country: Belgium

Publication language: English

Persistent website address: https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-178.pdf

Publication open access: Other way freely accessible online

Publication channel open access:

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/66333


Abstract

The minimal learning machine (MLM) training procedure consists in solving a linear system with multiple measurement vectors (MMV) created between the geometric con gurations of points in the input and output
spaces. Such geometric con gurations are built upon two matrices created using subsets of input and output points, named reference points (RPs). The present paper considers an extension of the focal underdetermined
system solver (FOCUSS) for MMV linear systems problems with additive noise, named regularized MMV FOCUSS (regularized M-FOCUSS), and evaluates it in the task of selecting input reference points for regression
settings. Experiments were carried out using UCI datasets, where the proposal was able to produce sparser models and achieve competitive performance when compared to the regular strategy of selecting MLM input RPs.


Keywords: machine learning


Contributing organizations


Related projects


Ministry reporting: Yes

Reporting Year: 2019

JUFO rating: 1


Last updated on 2021-10-06 at 19:03