Data Science Minor - Course Description
COSC 200 - Computational Methods for Image Analysis
- Signal and color/pixel/voxel image representation. Medical imaging acquisition. Filtering and convolution, low-pass/high-pass filters, bilateral filtering. Local feature detection and description. Morphological image processing, radon transform, geometric image transformation, interpolation. Data compression. Image comparison/categorization. Prerequisites: COSC 121 and either MATH 316, MATH 350, PSYC 250, SOC 250, POSC 250, ECON 212, BA 216, or COM 240.
COSC 210 - Introduction to Machine Learning
- Linear regression/classification. Decision trees. Support vector machines. Spectral methods, k-means clustering. Neural networks. Deep learning, gradient descent, back-propagation, error evaluation/cross-validation. Prerequisites: COSC 121 and either MATH 316, MATH 141, MATH 350, PSYC 250, SOC 250, or ECON 212
COSC 220 - Applied Data Science
- Project-based class using data science on a real-world problem from start (design, data-preparation/pre-processing) to finish (report of the results). This culminating practicum course for the Applied Data Science minor builds on one or more of the prerequisites. Topics include, but are not limited to, data mining, text mining, and applied machine learning. Prerequisite: COSC 210.
COSC 230 - Advanced Machine Learning
- Graph theory. Probabilistic graphical models. Bayes theorem. Parametric discrete Gaussian message passing. Non-parametric message passing. Prerequisites: MATH 260. COSC 210.
School: Seaver College
Accreditation: AACSB, WSCUC
- Fall 2021: COSC 210
- Spring 2022: COSC 200