This semilab introduces the intersection of computational methods and scientific inquiry. Students will develop practical skills in applying machine learning techniques to scientific problems through hands-on projects and problem-solving. We will explore probabilistic modeling for understanding uncertainty and making predictions, curve-fitting methods to discover mathematical relationships in experimental data, optimization techniques for solving complex scientific problems, and simple neural networks for pattern recognition and prediction.
You will gain foundational programming skills while learning to apply computational thinking to real scientific challenges. By the end of the course, you will have created your own machine-learning models to analyze scientific data and make meaningful predictions.
Prerequisites: Linear algebra, experience in a higher level programming language (Python, Matlab, Julia).