The Role of Mathematical Models in Artificial Intelligence and Machine Learning
Keywords:
Artificial intelligence, machine learning, mathematical models, neural network, probability theory, gradient descent, modeling.Abstract
This article analyzes the role of mathematical models in artificial intelligence and machine learning systems, as well as their importance in algorithm design. The relevance of the topic lies in the fact that as digital technologies continue to develop, the accuracy and stability of AI-based systems increasingly depend on mathematical modeling. The main objective of the study is to identify the functional role of key mathematical models used in machine learning algorithms, particularly linear algebra, probability theory, statistical models, and gradient optimization methods. The analysis shows that mathematical models enhance algorithm efficiency and improve learning quality. The research findings may be useful for both researchers conducting scientific studies in the field of artificial intelligence and developers of applied systems.
References
Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach. 4th ed. Pearson.
Khan, A. M., & Yoon, C. (2019). "A Survey on Mathematical Models in Machine Learning and AI." Journal of Machine Learning Research, 20, 1–26.
Haykin, S. (2009). Neural Networks and Learning Machines. 3rd ed. Pearson.
Müller, A. C., & Guido, S. (2016). Introduction to Machine Learning with Python. O'Reilly Media.
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning. 2nd ed. Springer.
Domingos, P. (2015). "The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World." Basic Books.
Wang, S., & Chan, H. L. (2021). "Mathematical Modelling in Artificial Intelligence." Mathematics and Computers in Simulation, 179, 103–120.
