The analysis of modern clustering and classification methods
Keywords:
classification, clustering, machine learning, artificial intelligence, neural networks, classification algorithmsAbstract
Over the past 20 years, machine learning methods have spread rapidly to most areas of human activity and now help to solve a variety of tasks from credit scoring and product price forecasting to car license plate recognition and speech synthesis. These methods are based on the tasks they solve. Currently, the most relevant and popular tasks are classification and clustering of objects. The article provides an overview and analysis of modern methods that can solve these types of problems.
References
Бишоп К.М. Распознавание образов и машинное обучение. М.: Вильямс, 2020. 960 с.
Andrew Y.Ng, Michael I. Jordan, Yair Weiss. On Spectral Clustering: Analysis and an algorithm // NIPS'01 : Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic. 2001. Р. 849–856.
Brendan J., Delbert Dueck. Clustering by Passing Messages Between Data Points // SCIENCE. 2007. V. 315. P. 972–976.
Gass S.I., John F. Magee, Assad A. Profiles in Operations Research // International Series in Operations Research & Management Science. 2011. V. 147. – https://doi.org/10.1007/978-1-4419-6281-2_33.
Leo Breiman. Random Forests // Machine Learning volume. 2001. 45. Р. 5–32.
Marcel R. Ackermann Analysis of Agglomerative Clustering // Algorithmica. 2014. 69. Р. 184– 215.
Tianqi Chen, Carlos Guestrin. XGBoost: A Scalable Tree Boosting System // KDD '16: Proceedings of the 22nd ACM SIGKDD // International Conference on Knowledge Discovery and Data Mining. 2016. Р. 785–794.
