Calculus for Artificial Intelligence focuses on understanding how AI models learn and improve. It covers limits, derivatives, gradients, and optimization techniques that are essential for training models. The course explains how calculus is used in loss functions, gradient descent, and neural networks, providing the mathematical foundation behind learning, prediction, and decision-making in AI systems.
This course introduces the fundamental concepts of Discrete Mathematics essential for Artificial Intelligence and Computer Science. Topics include logic, sets, relations, functions, graph theory, combinatorics, and recursion. The course emphasizes logical reasoning, problem-solving, and algorithmic thinking required for AI tasks such as search algorithms, decision trees, graph-based models, and knowledge representation. It provides a strong theoretical foundation for advanced studies in Artificial Intelligence, Machine Learning, and Data Science.
Probability and Statistics for Machine Learning explains how uncertainty and data variability are modeled in ML systems. It covers probability distributions, random variables, expectation, variance, and statistical inference. The course shows how these concepts are used in data analysis, model evaluation, prediction, and decision-making under uncertainty, forming a key foundation for modern machine learning algorithms.
Linear Algebra for Machine Learning introduces the core mathematical concepts behind ML algorithms. It explains how vectors and matrices represent data, how transformations work, and why ideas like eigenvalues and matrix decompositions are important for tasks such as dimensionality reduction. The course connects theory with practical machine learning applications, building a strong foundation for understanding and improving models.