This course covers the foundations of machine learning in healthcare systems including algorithms related to classification and regression prediction in supervised setting, clustering and dimension reduction in an unsupervised setting. Topics include data preprocessing and classification techniques such as logistic regression, support vector machines, KNN, Na'ive Bayes', ensemble methods such as random forests, boosted trees, XGBoost, dimension reduction techniques such as principal components analysis, t-distributed scholastic neighborhood embedding, ISOMAP, locally linear embedding, UMAP, multidimensional scaling.

In this course, students will work to develop a data science thesis project with both an outside mentor and a faculty advisor. This course essentially bridges the entire curriculum, but builds over the coursework to the final presentation at the students' second residency prior to completing the program. Each student on a team will be required to justify the completion of practicum hours.

In this course, students will work to develop a data science thesis project with both an outside mentor and a faculty advisor. This course essentially bridges the entire curriculum, but builds over the coursework to the final presentation at the students' second residency prior to completing the program. Each student on a team will be required to justify the completion of practicum hours.

In this seminar, UNH-4U students will explore career interests, develop career plans, and learn and practice skills needed to land a job or internship. Specific objectives include: 1) articulating career goals and competencies; 2) creating an academic and career development plan; 3) demonstrating skills for job and internship pursuit; and 4) engaging in professional networking. UNH-4U students can participate in the seminar up to 4 semesters with specific seminar activities established in consultation with mentor.