This project provides a hands-on training environment for both machine learning and deep learning concepts. It combines classical approaches such as regression models and classification models with practical deep learning experiments on the MNIST dataset. In addition, it integrates advanced mathematical foundations, including Gaussian Processes and other statistical techniques, to build a deeper understanding of predictive modeling.
-
Explore fundamental regression methods for numerical prediction.
-
Apply supervised classification algorithms to structured datasets.
-
Implement deep neural networks for image recognition using MNIST.
-
Study mathematical tools (e.g., Gaussian Processes) to understand uncertainty and model generalization.
This training is designed to strengthen both theoretical knowledge and programming skills, making it a solid foundation for anyone aiming to work in AI, data science, or applied machine learning research.