A4 Article in conference proceedings
Extreme Minimal Learning Machine (2018)
Kärkkäinen, T. (2018). Extreme Minimal Learning Machine. In ESANN 2018 : Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (pp. 237-242). ESANN. https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2018-72.pdf
JYU authors or editors
Publication details
All authors or editors: Kärkkäinen, Tommi
Parent publication: ESANN 2018 : Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Conference:
- European symposium on artificial neural networks, computational intelligence and machine learning
ISBN: 978-2-87587-047-6
Publication year: 2018
Pages range: 237-242
Publisher: ESANN
Publication country: Belgium
Publication language: English
Persistent website address: https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2018-72.pdf
Publication open access: Other way freely accessible online
Publication channel open access:
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/62746
Additional information: ESANN 2018 : 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, April 25-26-27, 2018.
Abstract
Extreme Learning Machine (ELM) and Minimal Learning Machine (MLM) are nonlinear and scalable machine learning techniques with randomly generated basis. Both techniques share a step where a matrix of weights for the linear combination of the basis is recovered. In MLM, the kernel in this step corresponds to distance calculations between the training data and a set of reference points, whereas in ELM transformation with a sigmoidal activation function is most commonly used. MLM then needs additional interpolation step to estimate the actual distance-regression based output. A natural combination of these two techniques is proposed here, i.e., to use a distance-based kernel characteristic in MLM in ELM. The experimental results show promising potential of the proposed technique.Extreme Learning Machine (ELM) and Minimal Learning Machine (MLM) are nonlinear and scalable machine learning techniques with randomly generated basis. Both techniques share a step where a matrix of weights for the linear combination of the basis is recovered. In MLM, the kernel in this step corresponds to distance calculations between the training data and a set of reference points, whereas in ELM transformation with a sigmoidal activation function is most commonly used. MLM then needs additional interpolation step to estimate the actual distance-regression based output. A natural combination of these two techniques is proposed here, i.e., to use a distance-based kernel characteristic in MLM in ELM. The experimental results show promising potential of the proposed technique.
Keywords: machine learning
Free keywords: Extreme Learning Machine; Minimal Learning Machine
Contributing organizations
Related projects
- Competitive funding to strengthen universities’ research profiles. Profiling actions at the JYU, round 3
- Hämäläinen, Keijo
- Research Council of Finland
- STRUCTURE PREDICTION OF HYBRID NANOPARTICLES VIA ARTIFICIAL INTELLIGENCE
- Kärkkäinen, Tommi
- Research Council of Finland
Ministry reporting: Yes
Reporting Year: 2018
JUFO rating: 1