This course aims to introduce students to fundamental optimization techniques and basic curve fitting methods from an applied point of view, with an emphasis on practicality. Students will learn the skills necessary to apply these techniques to real-world problems, enabling them to solve optimization problems and perform curve fitting for data analysis. Throughout the course, students will also gain proficiency in Julia programming language suitable for numerical analysis and optimization, equipping them with essential tools for practical applications in these fields.
Upon succesfull completion of this course students will be able to;
1. Gain a solid foundation in essential mathematical concepts, particularly in linear algebra and differential calculus, enabling them to solve complex numerical problems,
2. Acquire practical skills in optimization techniques, including gradient descent, steepest descent, and Newton's method, allowing them to solve optimization problems in machine learning efficiently,
3. Learn how to construct statistical models from scratch and understand how do they work under the hood,
4. Gain insights into deep learning and neural network development, including practical experience in building and training. Top of Form
5. Develop the ability to read, comprehend and apply contemporary research in the field of machine learning and deep learning to engage with the latest advancements and discoveries in the discipline.