Learning with similarity functions: A novel design for the extreme learning machine

Neurocomputing

Volumn 261, Issue , 2017, Pages 37-49

  Gastaldo, P ^a   Bisio, F ^a   Gianoglio, C ^a   Ragusa, E ^a   Zunino, R ^a  

^a UNIVERSITY OF GENOA   (Italy)

Author keywords

Extreme learning machine; Similarity functions; Single layer feedforward neural networks

Indexed keywords

ECONOMIC AND SOCIAL EFFECTS; FEEDFORWARD NEURAL NETWORKS; KNOWLEDGE ACQUISITION; MULTILAYER NEURAL NETWORKS; NETWORK LAYERS;

CLASSIFICATION ACCURACY; CONVENTIONAL APPROACH; EXTREME LEARNING MACHINE; LEARNING FRAMEWORKS; NOVEL INTERPRETATION; SIMILARITY FUNCTIONS; SINGLE LAYER FEED-FORWARD NEURAL NETWORKS; THEORY OF LEARNING;

MACHINE LEARNING;

ARTICLE; CONTROLLED STUDY; EXTREME LEARNING MACHINE; INFORMATION PROCESSING; LEARNING ALGORITHM; LEARNING THEORY; LEAST SQUARE ANALYSIS; LIMIT OF QUANTITATION; MACHINE LEARNING; MEASUREMENT ACCURACY; NERVE CELL; PRIORITY JOURNAL; PROBABILITY; RELIABILITY; SIMILARITY FUNCTION;

EID: 85014115331     PISSN: 09252312     EISSN: 18728286     Source Type: Journal    
DOI: 10.1016/j.neucom.2016.05.116     Document Type: Article

References (22)

1. Hornik, K., Stinchcombe, M., White, H., Multilayer feedforward networks are universal approximators. Neural Netw. 2 (1989), 359–366.
2. Lowe, D., Adaptive radial basis function nonlinearities, and the problem of generalization. Proceedings of the 1st IEE International Conference on Artificial Neural Networks, 1989, 171–175.
3. Pao, Y.H., Park, G.H., Sobajic, D.J., Learning and generalization characteristics of random vector functional-link net. Neurocomputing 6 (1994), 163–180.
4. Huang, G., Huang, G.-B., Song, S., You, K., Trends in extreme learning machines: a review. Neural Netw. 61 (2015), 32–48.
5. Decherchi, S., Gastaldo, P., Leoncini, A., Zunino, R., Efficient digital implementation of extreme learning machines for classification. IEEE Trans. Circ. Syst. II 50 (2012), 496–500.
6. Gastaldo, P., Pinna, L., Seminara, L., Valle, M., Zunino, R., A tensor-based pattern-recognition framework for the interpretation of touch modality in artificial skin systems. IEEE Sens. 14 (2014), 2216–2225.
7. Poria, S., Cambria, E., Winterstein, G., Huang, G.-B., Sentic patterns: dependency-based rules for concept-level sentiment analysis. Knowl. Based Syst. 69 (2014), 45–63.
8. Chen, H., Peng, J., Zhou, Y., Li, L., Pan, Z., Extreme learning machine for ranking: generalization analysis and applications. Neural Netw. 53 (2014), 119–126.
9. Grigorievskiy, A., Miche, Y., Ventelä, A.-M., Séverin, E., Lendasse, A., Long-term time series prediction using OP-ELM. Neural Netw. 51 (2014), 50–56.
10. Cambria, E., Gastaldo, P., Bisio, F., Zunino, R., An ELM-based model for affective analogical reasoning. Neurocomputing 149A (2015), 443–455.
11. Zhang, L., Zhang, D., Domain adaptation extreme learning machines for drift compensation in E-nose systems. IEEE Trans. Instrum. Meas., 64(7), 2015 1790-1780.
12. Bisio, F., Decherchi, S., Gastaldo, P., Zunino, R., Inductive bias for semi-supervised extreme learning machine. Neurocomputing 174 (2016), 154–167.
13. Balcan, M.F., Blum, A., Srebro, N., A theory of learning with similarity functions. Mach. Learn. 72 (2008), 89–112.
14. Gastaldo, P., Bisio, F., Decherchi, S., Zunino, R., SIM-ELM: Connecting the ELM model with similarity-function learning. Neural Netw. 74 (2016), 22–34.
15. http://www.csie.ntu.edu.tw/∼cjlin/libsvmtools/datasets/binary.html.
16. http://www.csie.ntu.edu.tw/∼cjlin/libsvmtools/datasets/multiclass.html.
17. Hofmann, T., Schölkopf, B., Smola, A.J., Kernel methods in machine learning. Ann. Stat. 36 (2008), 1171–1220.
18. Liu, X., Lin, S., Fang, J., Xu, Z., Is extreme learning machine feasible? a theoretical assessment (Part I). IEEE Trans. Neural Netw. Learn. Syst. 26 (2015), 7–20.
19. Liu, X., Lin, S., Fang, J., Xu, Z., Is extreme learning machine feasible? a theoretical assessment (Part II). IEEE Trans. Neural Netw. Learn. Syst. 26 (2015), 21–34.
20. Vapnik, V.N., Statistical Learning Theory. 1998, Wiley-Interscience Pub.
21. Anguita, D., Ghio, A., Oneto, L., Ridella, S., In-sample model selection for trimmed hinge loss support vector machine. Neural Process. Lett. 36:3 (2012), 275–283.
22. Anguita, D., Ghio, A., Oneto, L., Ridella, S., In-sample and out-of-sample model selection and error estimation for support vector machines. IEEE Trans. Neural Netw. Learn. Syst. 23:9 (2012), 1390–1406.