OPTIMIZATION OF TRAINING SAMPLE USING RANDOM POINT PROCESSES

2025;
: 109-118
1
Karpenko Physico-mechanical Institute of the NAS of Ukraine, Lviv, Ukraine
2
Karpenko Physico-Mechanical Institute of the National Academy of Sciences of Ukraine, Lviv, Ukraine
3
Karpenko Physico-mechanical Institute of the NAS of Ukraine, Lviv, Ukraine

The paper considers methods for optimizing training samples for deep learning algorithms through the use of random point processes, such as Matern of the first and second types, Gibbs, Gaussian, and Poisson processes. An approach to reducing training data without sacrificing informativeness is proposed, enabling a decrease in computational costs and mitigating the risk of overfitting. A novel method of representing images as random point processes is introduced, allowing a transition from the pixel based representation of an image to a model more suitable for analysis with point process techniques. This transition to a more compact empirical form facilitates subsequent analysis and modeling. In addition, it enables the use of statistical tools to uncover patterns hidden within images. The effectiveness of random point processes in shaping the feature space, analyzing coverage, and structuring the training dataset is demonstrated. The study also considers the impact of different types of point processes on data balance and their ability to reduce redundancy within the sample. Particular attention is given to the issue of data representativeness, as it directly affects the stability and generalization capability of deep learning models. Algorithms for converting images into point processes and their application for class balancing, data thinning, and enhancing the representativeness of samples are presented. The evaluation of classification accuracy, conducted using ResNet models, highlights the advantages of applying point processes over random data thinning. The results confirm the effectiveness of point processes for optimizing large-scale training datasets and improving the accuracy of deep learning. Furthermore, the findings indicate that these methods may play a key role in developing more lightweight and efficient neural network models. The study outlines promising directions for future research in adaptive optimization of training samples, where random point processes may serve as the foundation for new approaches to data preparation in neural network training.

[1]     Alzubaidi, L., Zhang, J., Humaidi, A., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. & Al-Amidie, M., (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 53. doi:10.1186/s40537-021-00444-8

[2]     Pichler, M. & Hartig, F., (2023). Machine learning and deep learning—A review for ecologists. Methods in Ecology and Evolution. doi:10.1111/2041-210X.14061

[3]     Awais, M., Chiari, L., Ihlen, E., Helbostad, J. & Palmerini, L., (2021). Classical Machine Learning versus Deep Learning for the Older Adults Free-Living Activity Classification. Sensors, 21. doi:10.3390/s21144669

[4]     Snell, J., Swersky, K. & Zemel, R., (2017). Prototypical Networks for Few-shot Learning. Advances in Neural Information Processing Systems (NeurIPS).

[5]     Mensink, T., Verbeek, J., Perronnin, F. & Csurka, G., (2013). Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost. IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]     Hart, P.E., (1968). The Condensed Nearest Neighbor Rule. IEEE Transactions on Information Theory, 14(3), pp.515–516.

[7]     Wilson, D.L., (1972). Asymptotic Properties of Nearest Neighbor Rules Using Edited Data. IEEE Transactions on Systems, Man, and Cybernetics, 2(3), pp.408–421.

[8]     Angelova, A., Zhu, S. & Yan, S., (2005). Pruning Training Sets for Learning of Object Categories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]     Settles, B., (2009). Active Learning Literature Survey. University of Wisconsin-Madison.

[10]  Sener, O. & Savarese, S., (2018). Active Learning for Convolutional Neural Networks: A Core-Set Approach. International Conference on Learning Representations (ICLR).

[11]  Bachem, O., Lucic, M. & Krause, A., (2017). Practical Coreset Constructions for Machine Learning. arXiv preprint.

[12]  Mirzasoleiman, B., Bilmes, J. & Leskovec, J., (2020). Coresets for Data-efficient Training of Machine Learning Models. arXiv preprint.

[13]  Hinton, G.E. & Salakhutdinov, R.R., (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), pp.504–507. doi:10.1126/science.1127647

[14]  Qi, C.R., Su, H., Mo, K. & Guibas, L.J., (2017). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. CVPR.

[15]  Huang, S., Zhang, Y., Deng, J. & Yu, K., (2020). Deep Prototype Learning for Classification. In: International Conference on Learning Representations (ICLR).

[16]  Bengio, Y., Louradour, J., Collobert, R. & Weston, J., (2009). Curriculum Learning. Advances in Neural Information Processing Systems (NeurIPS).

[17]  Tran, K., Nguyen, M., Phung, D. & Venkatesh, S., (2021). Transferable Prototype Learning across Domains. arXiv preprint