Full course description
This course provides an application-focused introduction to the mathematical foundations essential for Artificial Intelligence, emphasizing their role throughout the AI Project Cycle. Participants will explore key concepts from Statistics, Probability, and Linear Algebra, developing a deep appreciation for how mathematics underpins AI systems. Through hands-on exercises using Python, learners will apply these concepts to real-world datasets—practicing data transformation, sampling, feature extraction, and model evaluation. The course introduces descriptive and inferential statistics, matrix operations, and dimensionality reduction techniques such as PCA and SVD. Additionally, learners will engage with probability-driven approaches including Bayes Theorem, enhancing their understanding of classification and optimization tasks. Ethical considerations such as data bias, along with the use of industry dashboards, are addressed to promote responsible AI practices. Designed to build both theoretical understanding and practical application, the course equips participants to leverage core mathematical tools in optimizing AI models and making data-informed decisions.