Food Science 790D - Appl Food DataSci & Modeling

This course introduces graduate students in Food Science to the principles and applications of data science, machine learning, and deep learning for analyzing complex food systems. Students learn to organize, visualize, and model experimental data such as kinetic, rheological, spectroscopic, imaging, and process data using Python in a cloud-based environment. Topics include exploratory data analysis, regression and classification, multivariate calibration, and modern deep learning approaches for nonlinear feature extraction, including autoencoders and nonlinear PCA. Emphasis is placed on applying these computational tools to real food datasets to reveal structure?function relationships and improve formulation and processing design. Designed for students with minimal coding or mathematical background, the course integrates conceptual lectures, hands-on coding labs, and a project-based learning component.

Open to FOOD-SCI grad students.