IMPLEMENTING DOCUMENT CLASSIFICATION IN PYTHON AND EVALUATING RESULTS
Аннотация
In our article, we will cover general information about machine learning, its main types, as well as the most important libraries for machine learning in Python. Machine learning is one of the main methods for demonstrating data science in general. In machine learning, the computational and algorithmic capabilities of data science are combined with approaches, and the result is a set of data mining approaches, mainly related to the efficiency and theory of computation. Document classification plays an important role in the archiving department, they classify pre-defined documents and store them in a digital archive. Relevance of the topic In digital archives, document classification is an important process for many document preservation organizations. In the course of the study, a technology for testing the use of deep learning algorithms is being created. Deep learning, i.e. deep structured learning, is part of a broad group of machine learning methods based on artificial neural networks. Learning cannot be controlled, partially controlled or controlled.
Автор
A. S. Baimakhanova
K. M. Berkimbayev
Eşref Adalı
G. S. Iskendirova
DOI
doi.org/10.48081/UPDW5717
Ключевые слова
Machine learning
Artificial neural networks
Python
Scikit-learn
Keras
TensorFlow
Год
2023
Номер
Выпуск 1