Undergraduate Courses 2022-23

Basics of Chemometrics; Database mining (CSD and PDB); Multivariate data sets, statistics and data reduction; Data analysis and visualization; Molecular representation and chemical descriptors (e.g. SMILES / SMARTS patterns); Application to structure-based drug design.

A concise introduction to multivariable calculus using numerical computing software. Fundamental concepts from multivariable calculus with emphasis on applications and calculations using software. Topics from vectors, curves and parametric equations, differentiation in several variables, applications in approximation, optimization and gradient descent algorithm, and integration in several variables.

This course provides an introduction to linear algebra using numerical computing software. Topics include systems of linear equations, matrix algebra and determinants, eigenvalue and eigenvector, eigenvalue decomposition, singular value decomposition (SVD) and least square problems.

Introduction to the fundamental concepts and techniques of object-oriented programming, including classes, objects, heritage, polymorphism, modularization and associations, etc.

A survey on data collection and applied data science in different areas of science and in the society as a whole. Examples and case studies will be taken from physics, chemistry, life science and ocean science as well as other disciplines that are heavily data driven. Graded DI, PA or F.

The course is designed for students who are new to data science and provides them with a basic training of probability and statistics. Some ideas and principles of data analytics with probability and statistics are covered. In addition to the knowledge of data, students will learn some data analytical skills and have hands-on experience of processing and analyzing real datasets by using a software like R or Python.

This is a continuation of DASC 2110. It covers the object-oriented view of data structures, including linked list, queues, and stacks; and algorithms including recursion, sorting, and searching. Students are expected to understand and use these techniques to handle data.

Concepts and techniques in the field of statistical modeling will be introduced. Materials include the models used to explore different sorts of data for the discovery of predictive models and knowledge. The course will include models such as linear regression models, logistic regression models, support vector machines, decision trees, random forest, ensemble models, nearest neighbor, clustering, as well as spatial models, time-series models, quantile regression models, and network models. R or Python will be covered. Students will also gain hands-on experience with data analytical tools from various applications in sciences.

Data visualization is the graphical representation of applied data science. It can also provide us with a powerful way to communicate data-driven findings, motivate analyses, and detect flaws in an infographic or dashboard. This course illustrates how to use the techniques of data visualization and discovery tools to explore, visualize and analyze data. By the end of the course, students will be able to utilize tools and packages in R or Python to enhance their skills on science communication.

This course introduces numerical methods for various data analytic tools. Topics include numerical algorithms for linear systems, eigenvalues and eigenvectors, nonlinear equations, interpolation and approximation, numerical integration and solution of ordinary differential equations, fundamental theory and techniques of constrained and unconstrained optimizations, fundamental techniques and software for machine learning. Examples are taken from various applications in both physical and life sciences.

Students are expected to complete a project in an area of their study tracks under the guidance of a faculty member. It provides an opportunity for students to integrate those mathematical and data analytics techniques they learned to analyze a data intensive problem in science. For DASC students in their fourth year of study only.

This course introduces various case studies drawn from different areas of data and information sciences to illustrate the use of data analytics as a problem-solving tool. Topics include recommendation systems, data from social media and FinTech. Each application integrates mathematical models, numerical techniques and computer implementations into a coherent perspective.

The goal of the course is to learn basic numerical analysis tools needed to compute and practice simple techniques for analyzing oceanographic data. These analysis include basic statistics, curve fitting, and simple graphics. Students will learn these techniques through examples from ocean data sets. Students will learn to conduct these analyses with Python or R and are not assumed to have experience in programming.