Abstract
The relationships between features can guide the architecture of pattern recognition systems. It is the case with images where the spatial relationship of pixels allows to use convolutions to filter images and extract high level features. In this paper, we consider extreme learning machine (ELM) classifiers and propose to modify the selection of the inputs of a hidden unit based on correlation matrix of the input features. The proposed approach is tested on databases of handwritten digits (MNIST and Devanagari). The results show that input selection based on the correlation matrix provides better performance and leads to a sparse representation of the weights in the network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akusok, A., Bjƶrk, K.M., Miche, Y., Lendasse, A.: High-performance extreme learning machines: a complete toolbox for big data applications. IEEE Access 3, 1011ā1025 (2015). https://doi.org/10.1109/ACCESS.2015.2450498
Alhamdoosh, M., Wang, D.: Fast decorrelated neural network ensembles with random weights. Inf. Sci. 264, 104ā117 (2014)
Bhattacharya, U., Chaudhuri, B.: Databases for research on recognition of handwritten characters of indian scripts. In: Proceedings of the 8th International Conference on Document Analysis and Recognition (ICDAR 2005), pp. 789ā793 (2005)
Cecotti, H.: Deep random vector functional link network for handwritten character recognition. In: Proceedings of the International Joint Conference on Neural Networks, pp. 1ā6 (2016)
Chen, C.L.P.: A rapid supervised learning neural network for function interpolation and approximation. IEEE Trans. Neural Networks 7(5), 1220ā1230 (1996)
Chen, C.L.P., Wan, J.Z.: A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction. IEEE Trans. Syst. Man Cybern. Part B 29(1), 62ā72 (1999)
Huang, G.B., Saratchandran, P., Sundararajan, N.: A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation. IEEE Trans. Neural Networks 16(1), 57ā67 (2005)
Huang, G.B., Siew, C.K.: Extreme learning machine with randomly assigned RBF kernels. Int. J Inf. Technol. 11(1), 16ā24 (2005)
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: a new learning scheme of feedforward neural networks. In: Proceedings of IEEE International Joint Conference on Neural Networks, vol. 2, pp. 985ā990 (2004)
Igelnik, B., Pao, Y.H.: Stochastic choice of basis functions in adaptive function approximation and the functional-link net. IEEE Trans. Neural Networks 6(6), 1320ā1329 (1995)
Kasun, L.L.C., Zhou, H., Huang, G.B., M., V.C.: Representational learning with extreme learning machine for big data. IEEE Intell. Syst. 28(6), 31ā34 (2013)
Pal, U., Chaudhuri, B.B.: Indian script character recognition: a survey. Pattern Recogn. 37(9), 1887ā1899 (2004)
Pao, Y.H., Takefuji, Y.: Functional-link net computing: theory, system architecture, and functionalities. Computer 25(5), 76ā79 (1992)
Savojardo, C., Fariselli, P., Casadio, R.: BETAWARE: a machine-learning tool to detect and predict transmembrane beta-barrel proteins in prokaryotes. Bioinformatics 29(4), 504ā505 (2013)
Scardapane, S., Wang, D., Panella, M., Uncini, A.: Distributed learning for random vector functional-link networks. Inf. Sci. 301, 271ā284 (2015)
Schmidt, W.F., Kraaijveld, M.A., Duin, R.P.W.: Feedforward neural networks with random weights. In: Proceedings of 11th IAPR International Conference on Pattern Recognition, Conference B: Pattern Recognition Methodology and Systems, vol. 2, pp. 1ā4 (1992)
Tang, J., Deng, C., Huang, G.B.: Extreme learning machine for multilayer perceptron. IEEE Trans. Neural Networks Learn. Syst. 27(4), 809ā21 (2016)
Wang, L.P., Wan, C.R.: Comments on the extreme learning machine. IEEE Trans. Neural Networks 19(8), 1494ā1495 (2008)
Zhu, W., Miao, J., Qing, L.: Constrained extreme learning machines: a study on classification cases. arXiv preprint arXiv:1501.06115 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cecotti, H. (2022). Extreme Machine Learning Architectures Based onĀ Correlation. In: Vergara-Villegas, O.O., Cruz-SĆ”nchez, V.G., Sossa-Azuela, J.H., Carrasco-Ochoa, J.A., MartĆnez-Trinidad, J.F., Olvera-LĆ³pez, J.A. (eds) Pattern Recognition. MCPR 2022. Lecture Notes in Computer Science, vol 13264. Springer, Cham. https://doi.org/10.1007/978-3-031-07750-0_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-07750-0_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-07749-4
Online ISBN: 978-3-031-07750-0
eBook Packages: Computer ScienceComputer Science (R0)