Abstract
Contextual neural networks are generalization of multilayer neural networks. They possess interesting property of automatic selection of data attributes needed for correct processing of given input vectors. To achieve that they are using neurons with conditional, multistep aggregation functions and error generalized error backpropagation algorithm based on self-consistency paradigm. According to the literature of the subject, currently there are no implementations of those models in high-performance machine learning platforms like Mahout or MLlib. In this paper we present initial results of implementation of contextual neural networks in distributed machine learning framework called H2O. The motivation behind this work is the need to analyze properties of contextual neural networks and conditional multi-step aggregation functions while solving large classification problems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Grolinger, K., Capretz, M.A.M., Seewald, L.: Energy consumption prediction with big data: balancing prediction accuracy and computational resources. In: 2016 IEEE International Congress on Big Data (BigData Congress), pp. 1–8 (2016)
Ng, S.S.Y., Zhu, W., Tang, W.W.S., Wan, L.C.H., Wat, A.Y.W.: An independent study of two deep learning platforms - H2O and SINGA. In: 2016 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), pp 1–5. IEEE Press, Bali (2016)
Niu, F., Recht, B., Christopher, R., Wright, S.J.: HOGWILD!: a lock-free approach to parallelizing stochastic gradient descent. In: Advances in Neural Information Processing Systems, pp. 693–701 (2011)
Richter, A.N., Khoshgoftaar, T.M., Landset, S., Hasanin, T.: A multi-dimensional comparison of toolkits for machine learning with big data. In: 2015 IEEE International Conference on Information Reuse and Integration, pp. 1–8. IEEE, San Francisco (2015)
Suleiman, D., Al-Naymat, G.: SMS spam detection using H2O framework. Procedia Comput. Sci. 113, 154–161 (2017)
Domingos, S.L., Carvalho, R.N., Carvalho, R.S., Ramos, G.N.: Identifying IT purchases anomalies in the Brazilian government procurement system using deep learning. In: 15th IEEE International Conference on Machine Learning and Applications (ICMLA) (2016)
Al Najada, H., Mahgoub, I.: Big vehicular traffic data mining: towards accident and congestion prevention. In: International Wireless Communications and Mobile Computing Conference, pp. 256–261 (2016)
Huk, M.: Measuring the effectiveness of hidden context usage by machine learning methods under conditions of increased entropy of noise. In: 3rd IEEE International Conference on Cybernetics, pp. 1–6. IEEE Press (2017)
Liang, M., Trejo, C., Muthu, L., Ngo, L.B., Luckow, A., Apon, A.W.: Evaluating R-based big data analytic frameworks. In: 2015 IEEE International Conference on Cluster Computing (CLUSTER), pp. 1–2. IEEE, Chicago (2015)
Cook, D.: Practical Machine Learning with H2O Powerful, Scalable Techniques for Deep Learning and AI. O’Reilly Media, Newton (2016)
Huk, M.: Notes on the generalized backpropagation algorithm for contextual neural net-works with conditional aggregation functions. J. Intell. Fuzzy Syst. 32, 1365–1376 (2017)
Huk, M.: Backpropagation generalized delta rule for the selective attention Sigma-if artificial neural network. Int. J. Appl. Math. Comput. Sci. 22, 449–459 (2012)
Huk, M.: Learning distributed selective attention strategies with the Sigma-if neural network. In: Akbar, M., Hussain, D. (eds.) Advances in Computer Science and IT, pp. 209–232. InTech, Vukovar (2009)
Huk, M., Pietraszko, J.: Contextual neural-network based spectrum prediction for cognitive radio. In: 4th International Conference on Future Generation Communication Technology (FGCT 2015), pp. 1–5. IEEE Computer Society, London (2015)
Huk, M.: Context injection as a tool for measuring context usage in machine learning. In: Nguyen, N.T., Tojo, S., Nguyen, L.M., Trawiński, B. (eds.) ACIIDS 2017. LNCS (LNAI), vol. 10191, pp. 697–708. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54472-4_65
Szczepanik, M., Jóźwiak, I.: Data management for fingerprint recognition algorithm based on characteristic points’ groups. In: Pechenizkiy, M., Wojciechowski, M. (eds.) New Trends in Databases and Information Systems. Advances in Intelligent Systems and Computing, vol. 185, pp. 425–432. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-32518-2_40
Huk, M.: Using context-aware environment for elderly abuse prevention. In: Nguyen, N.T., Trawiński, B., Fujita, H., Hong, T.-P. (eds.) ACIIDS 2016. LNCS (LNAI), vol. 9622, pp. 567–574. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-662-49390-8_55
Huk, M.: Context-related data processing with artificial neural networks for higher reliability of telerehabilitation systems. In: 17th International Conference on E-health Networking, Application & Services (HealthCom), pp. 217–221. IEEE Computer Society, Boston (2015)
Huk, M., Kwasnicka, H.: The concept and properties of sigma-if neural network. In: Ribeiro, B., Albrecht, R.F., Dobnikar, A., Pearson, D.W., Steele, N.C. (eds.) Adaptive and Natural Computing Algorithms, pp. 13–17. Springer, Vienna (2005). https://doi.org/10.1007/3-211-27389-1_4
Huk, M.: Sigma-if neural network as the use of selective attention technique in classification and knowledge discovery problems solving. Ann. UMCS Sectio AI – Inf. 4(2), 121–131 (2006)
Huk, M.: Manifestation of selective attention in Sigma-if neural network. In: 2nd International Symposium Advances in Artificial Intelligence and Applications, International Multiconference on Computer Science and Information Technology IMCSIT/AAIA 2007, vol. 2, pp. 225–236 (2007)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Privitera, C.M., Azzariti, M., Stark, L.W.: Locating regions-of-interest for the Mars Rover expedition. Int. J. Remote Sens. 21, 3327–3347 (2000)
Mel, B.W.: The Clusteron: toward a simple abstraction for a complex neuron. In: Advances in Neural Information Processing Systems, vol. 4, pp. 35–42. Morgan Kaufmann (1992)
Spratling, M.W., Hayes, G.: Learning synaptic clusters for nonlinear dendritic processing. Neural Process. Lett. 11, 17–27 (2000)
Raczkowski, D., Canning, A.: Thomas-Fermi charge mixing for obtaining self-consistency in density functional calculations. Phys. Rev. B 64, 121101–121105 (2001)
UCI Machine Learning Repository. http://archive.ics.uci.edu/ml
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Janusz, B.J., Wołk, K. (2018). Implementing Contextual Neural Networks in Distributed Machine Learning Framework. In: Nguyen, N., Hoang, D., Hong, TP., Pham, H., Trawiński, B. (eds) Intelligent Information and Database Systems. ACIIDS 2018. Lecture Notes in Computer Science(), vol 10752. Springer, Cham. https://doi.org/10.1007/978-3-319-75420-8_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-75420-8_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-75419-2
Online ISBN: 978-3-319-75420-8
eBook Packages: Computer ScienceComputer Science (R0)