Open    Access



Research on the Applications of Probability Theory in Artificial Intelligence



Author(s)

HAO Shun-li

Full-Text PDF XML     125 Views

DOI:10.17265/1539-8080/2026.06.002

Beijing International Studies University, Beijing, China

 Artificial intelligence (AI) aims to simulate the thinking process of human perception, learning, and decision-making, but uncertainty problems, such as data noise, information loss, and semantic ambiguity are commonly present in real environments. Traditional deterministic mathematics is difficult to complete modeling and inference in complex scenarios. Probability theory, as a mathematical branch that studies the statistical laws of random phenomena, can quantify the likelihood of events occurring and provide a theoretical basis for uncertainty reasoning, parameter optimization, and distribution modeling for AI. This paper focuses on core probability knowledge, such as conditional probability, Bayesian formula, and probability distribution. It systematically discusses the specific applications of probability theory in traditional machine learning, deep learning, generative AI, natural language processing, computer vision, and reinforcement learning. It summarizes the supporting role of probability theory in the development of AI and looks forward to the research direction of the integration of the two in combination with current technological trends.

probability theory, artificial intelligence, machine learning, deep learning

HAO Shun-li. Research on the Applications of Probability Theory in Artificial Intelligence.US-China Foreign Language, June 2026, Vol. 24, No. 6, 217-221 doi:10.17265/1539-8080/2026.06.002