Mathematical Modelling and Applied Mathematics

• ›Mathematical modelling of real-world systems
• ›Differential equations, dynamical systems, and scientific computing
• ›Graphs, networks, and complex systems modelling
• ›Data-driven and hybrid modelling for prediction and decision-making

Statistics, Data Science, and Machine Learning

• ›Statistical learning foundations and uncertainty quantification
• ›Bayesian and probabilistic modelling
• ›Experimental design, inference, and hypothesis testing for data-driven studies
• ›Big data analytics and high-dimensional statistics

Mathematical Methods in Imaging and Computer Vision

• ›Linear algebra, geometry, and transforms for imaging
• ›Variational methods, PDEs, and optimization in image processing
• ›Feature extraction, inverse problems, and image reconstruction
• ›Deep learning for vision: theory, interpretability, and evaluation

Learning, Prediction, and Decision Models

• ›Classification/regression models: theory and practice
• ›Loss functions, regularization, generalization, and model selection
• ›Kernel methods, SVMs, ensembles, and modern predictors
• ›Evaluation metrics, error analysis, robustness, and fairness

Optimization and Numerical Algorithms

• ›Convex and non-convex optimization (for ML and scientific applications)
• ›Gradient-based, stochastic, and proximal algorithms
• ›Numerical linear algebra for large-scale problems
• ›Distributed, parallel, and efficient optimization methods

Artificial Intelligence for Didactics and Mathematics Education

• ›Intelligent tutoring systems and adaptive learning
• ›AI tools for teaching and learning mathematics
• ›Learning analytics and educational data mining

Strengthen the Mathematical Foundations of AI

Explore modelling, dynamical systems, differential equations, and graph/network approaches that power intelligent systems.

Get Practical with Statistics & Data Science

Learn about statistical learning, Bayesian/probabilistic models, inference, and big-data methods for high-dimensional problems.

Sharpen Learning Theory for Classification & Regression

Discuss loss functions, regularization, generalization, kernels/SVMs, and evaluation methods to improve supervised learning.

Discover the Math Behind Computer Vision

Connect linear algebra, geometry, PDEs, optimization, and deep learning to vision tasks like reconstruction and recognition.

Master Optimization & Numerical Methods

Dive into convex/non-convex optimization, stochastic algorithms, numerical linear algebra, and scalable training techniques.

AI for Education & Mathematics Learning

See how intelligent tutoring, adaptive learning, and learning analytics can transform mathematics education.