Abstract
This paper discusses a specific problem in the study of deep neural networks - learning on small data. Such issue happens in situation of transfer learning or applying known solutions on new tasks that involves usage of particular small portions of data. Based on previous research, some specific solutions can be applied to various tasks related to machine learning, computer vision, natural language processing, medical data study and many others. These solutions include various methods of general purpose machine and deep learning, being successfully used for these tasks. In order to do so, the paper carefully studies the problems arise in the preparation of data. For benchmark purposes, we also compared “in wild” the methods of machine learning and identified some issues in their practical application, in particular usage of specific hardware. The paper touches some other aspects of machine learning by comparing the similarities and differences of singular value decomposition and deep constrained auto-encoders. In order to test our hypotheses, we carefully studied various deep and machine learning methods on small data. As a result of the study, our paper proposes a set of solutions, which include the selection of appropriate algorithms, data preparation methods, hardware optimized for machine learning, discussion of their practical effectiveness and further improvement of approaches and methods described in the paper. Also, some problems were discussed, which have to be addressed in the following papers.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Albtoush, A., Fernández-Delgado, M., Cernadas, E., Barro, S.: Quick extreme learning machine for large-scale classification. Neural Comput. Appl. 34(8), 5923–5938 (2021). https://doi.org/10.1007/s00521-021-06727-8
Aloysius, N., Geetha, M.: A review on deep convolutional neural networks. In: 2017 International Conference on Communication and Signal Processing (ICCSP), pp. 588–592. IEEE (2017). https://doi.org/10.1109/iccsp.2017.8286426
Alzubaidi, L., et al.: Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J. Big Data 8(1), 1–74 (2021). https://doi.org/10.1186/s40537-021-00444-8
Babichev, S., Durnyak, B., Zhydetskyy, V., Pikh, I., Senkivskyy, V.: Application of optics density-based clustering algorithm using inductive methods of complex system analysis. In: 2019 IEEE 14th International Conference on Computer Sciences and Information Technologies (CSIT), vol. 1, pp. 169–172 (2019). https://doi.org/10.1109/STC-CSIT.2019.8929869
Chan, D., Rao, R., Huang, F., Canny, J.: T-SNE-CUDA: GPU-accelerated T-SNE and its applications to modern data. In: 2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), pp. 330–338. IEEE (2018). https://doi.org/10.1109/cahpc.2018.8645912
Chawla, N., Bowyer, K., Hall, L., Kegelmeyer, W.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. (JAIR) 16, 321–357 (2002). https://doi.org/10.1613/jair.953
Dongarra, J., Gates, M., Haidar, A., et al.: The singular value decomposition: anatomy of optimizing an algorithm for extreme scale. SIAM Rev. 60(4), 808–865 (2018). https://doi.org/10.1137/17m1117732
Hast, A., Vast, E.: Word recognition using embedded prototype subspace classifiers on a new imbalanced dataset. J. WSCG 29(1–2), 39–47 (2021). https://doi.org/10.24132/jwscg.2021.29.5
He, H., Bai, Y., Garcia, E., Li, S.: ADASYN: adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp. 1322–1328. IEEE (2008). https://doi.org/10.1109/ijcnn.2008.4633969
Huang, G., Chen, D., Li, T., Wu, F., van der Maaten, L., Weinberger, K.Q.: Multi-Scale Dense Networks for Resource Efficient Image Classification (2017). https://doi.org/10.48550/arXiv.1703.09844
Izonin, I., Tkachenko, R., Gregus, M., Duriagina, Z., Shakhovska, N.: PNN-SVM approach of Ti-based powder’s properties evaluation for biomedical implants production. Comput. Mater. Continua 71(3), 5933–5947 (2022). https://doi.org/10.32604/cmc.2022.022582
Izonin, I., Tkachenko, R., Shakhovska, N., Lotoshynska, N.: The additive input-doubling method based on the SVR with nonlinear Kernels: small data approach. Symmetry 13(4), 1–18 (2021). https://doi.org/10.3390/sym13040612
Jiang, M., et al.: Text classification based on deep belief network and softmax regression. Neural Comput. Appl. 29(1), 61–70 (2016). https://doi.org/10.1007/s00521-016-2401-x
Khan, A., Sohail, A., Zahoora, U., Qureshi, A.S.: A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 53(8), 5455–5516 (2020). https://doi.org/10.1007/s10462-020-09825-6
Krak, I., Barmak, O., Manziuk, E.: Using visual analytics to develop human and machine-centric models: a review of approaches and proposed information technology. Comput. Intell. 1–26 (2020). https://doi.org/10.1111/coin.12289
Krak, Y., Barmak, A., Baraban, E.: Usage of NURBS-approximation for construction of spatial model of human face. J. Autom. Inf. Sci. 43(2), 71–81 (2011). https://doi.org/10.1615/jautomatinfscien.v43.i2.70
Krivonos, Y.G., Krak, Y., Barchukova, Y., Trotsenko, B.: Human hand motion parametrization for Dactilemes modeling. J. Autom. Inf. Sci. 43(12), 1–11 (2011). https://doi.org/10.1615/JAutomatInfScien.v43.i12.10
Kryvonos, I., Krak, I.: Modeling human hand movements, facial expressions, and articulation to synthesize and visualize gesture information. Cybern. Syst. Anal. 47(4), 501–505 (2011). https://doi.org/10.1007/s10559-011-9332-4
Kryvonos, I.G., Krak, I.V., Barmak, O.V., Ternov, A.S., Kuznetsov, V.O.: Information technology for the analysis of mimic expressions of human emotional states. Cybern. Syst. Anal. 51(1), 25–33 (2015). https://doi.org/10.1007/s10559-015-9693-1
Lytvynenko, V., Lurie, I., Krejcí, J., Voronenko, M., Savina, N., Ali Taif, M.: Two step density-based object-inductive clustering algorithm. In: Workshop Proceedings of the 8th International Conference on “Mathematics. Information Technologies. Education” (MoMLeT and DS-2019), vol. 2386, pp. 1–19. CEUR-WS, Shatsk, Ukraine (2019). http://ceur-ws.org/Vol-2386/paper10.pdf
Lytvynenko, V., Savina, N., Krejcí, J., Voronenko, M., Yakobchuk, M., Kryvoruchko, O.: Bayesian networks’ development based on noisy-MAX nodes for modeling investment processes in transport. In: Workshop Proceedings of the 8th International Conference on “Mathematics. Information Technologies. Education" (MoMLeT and DS-2019), vol. 2386, pp. 1–10. CEUR-WS, Shatsk, Ukraine (2019). http://ceur-ws.org/Vol-2386/paper1.pdf
Menardi, G., Torelli, N.: Training and assessing classification rules with imbalanced data. Data Min. Knowl. Disc. 28(1), 92–122 (2012). https://doi.org/10.1007/s10618-012-0295-5
Python: An open-source programming language, environment and interpreter (2022). https://www.python.org/about/
Romanuke, V.: An attempt of finding an appropriate number of convolutional layers in CNNs based on benchmarks of heterogeneous datasets. Electr. Control. Commun. Eng. 14(1), 51–57 (2018). https://doi.org/10.2478/ecce-2018-0006
Sultana, F., Sufian, A., Dutta, P.: Advancements in image classification using convolutional neural network. In: 2018 Fourth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), pp. 122–129. IEEE (2018). https://doi.org/10.1109/icrcicn.2018.8718718
TensorFlow: A system for large-scale machine learning (2022). https://www.tensorflow.org/about/
TensorFlow-DirectML: Github repository for tensorflow fork accelerated by directml (2022). https://github.com/microsoft/tensorflow-directml
Vahdat, A., Kautz, J.: Nvae: A deep hierarchical variational autoencoder (2020). 1048550/arXiv. 2007.03898
Wiatowski, T., Bolcskei, H.: A mathematical theory of deep convolutional neural networks for feature extraction. IEEE Trans. Inf. Theory 64(3), 1845–1866 (2018). https://doi.org/10.1109/tit.2017.2776228
Yona, G., Moran, S., Elidan, G., Globerson, A.: Active Learning with Label Comparisons (2022). https://doi.org/10.48550/ARXIV.2204.04670
Zebari, R., Abdulazeez, A., Zeebaree, D., et al.: A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction. J. Appl. Sci. Technol. Trends 1(2), 56–70 (2020). https://doi.org/10.38094/jastt1224
Zhang, G., Chen, Y.: More informed random sample consensus. arXiv (2020). https://doi.org/10.48550/ARXIV.2011.09116
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Krak, I., Kuznetsov, V., Kondratiuk, S., Azarova, L., Barmak, O., Padiuk, P. (2023). Analysis of Deep Learning Methods in Adaptation to the Small Data Problem Solving. In: Babichev, S., Lytvynenko, V. (eds) Lecture Notes in Data Engineering, Computational Intelligence, and Decision Making. ISDMCI 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 149. Springer, Cham. https://doi.org/10.1007/978-3-031-16203-9_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-16203-9_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16202-2
Online ISBN: 978-3-031-16203-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)