Infopaket

Models and methods of machine learning

ДВС.1.04

Вибіркова дисципліна для ОП

Second

2023/2024

3 Semester

3

PLO 3. To implement modern methods and techniques, namely informational, in order to perform a successful and effective professional activity and guarantee the quality of research in an applied linguistics field. PLO 21.1. To apply professionally the knowledge of basic methods and principles of data extraction (Data Mining), an intellectual analysis of text data (Text Mining), organization and types of artificial neural networks, and types of machine learning tasks in the domain of Automatic natural language processing. PLO 22.1. To know and apply systematically the methods of analysis and applied (linguistic) industry modeling, determine the information needs and data collection to design software. PLO 25.1. To choose paradigms and programming languages to solve the Applied Linguistics problems, apply the system and specialized tools, component technologies (platforms), and integrated environments of software development. PLO 27.1

Full-time form

1. To know: the basics of the disciplines "Programming", "Discrete mathematics", "Probability theory", and "Construction and analysis of algorithms". 2. To be able to apply information technologies and programming languages ​​to solve applied problems and conduct scientific research. 3. To have basic skills in combining and analyzing algorithms, and programming in Python / Java / C++ languages. 4. To know English and English language terminology in the studied field.

The purpose of the discipline "Models and Methods of machine learning" is to obtain the necessary knowledge of modern information and intellectual technologies and the skills of their practical application for research and programming processes for solving complex problems of natural language text processing. As a result of studying the educational discipline, the student has: To know the main models, methods, and algorithms used to build machine learning systems. To be able to develop machine learning systems using modern technologies and programming languages ​​(specialized libraries for developing machine learning models, natural language processing, etc.).

1. Rish, Irina. (2001). «An empirical study of the naive Bayes classifier». IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence. 2. Карташов М. В. Імовірність, процеси, статистика — Київ, ВПЦ Київський університет, 2007. 3. Hosmer, David W., Stanley Lemeshow (2000). Applied Logistic Regression, 2nd ed.. New York; Chichester, 4. Harremoës P. and Topsøe F., 2001, Maximum Entropy Fundamentals, Entropy, 3(3), 191—226. 5. Nello Cristianini, John Shawe-Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. — Cambridge University Press, 2000. 6. Lawrence Rabiner. A tutorial on Hidden Markov Models and selected applications in speech recognition. Proceedings of the IEEE 77 (2): 257–286. 7. Lafferty, J., McCallum, A., Pereira, F. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proc. 18th International Conf. on Machine Learning. Morgan Kaufmann. с. 282–289.

Lectures, practical classes, independent work.

Student evaluation forms: - semester assessment: 1. Control test 1: 7 points / 5 points. 2. Control test 2: 8 points / 5 points. 3. Laboratory work 1 (project): 15 points / 10 points. 4. Laboratory work 2 (project): 15 points / 10 points. 5. Laboratory work 3 (project): 15 points / 10 points. 6. Final test: 40 points / 20 points Types of tasks for the final test: 8 tests and 6 tasks in written form. The discipline ends with a credit. The final number of points for the discipline (maximum 100 points) is defined as the sum of points for systematic work during the semester, taking into account the final test.

Ukrainian, English