This course trains students in data visualization, the graphical communication of data and information for presentation, confirmation, and exploration. Students learn the stages of the visualization pipeline, including data characterization, mapping data attributes to graphical attributes, user task abstraction, visual display techniques, tools, paradigms, and perceptual issues. Students evaluate the effectiveness of visualizations for specific data, task, and user types. Students implement visualization algorithms and undertake projects involving the use of commercial and public-domain visualization tools.
Cat I (offered at least 1x per Year). This course provides an introduction to the core concepts in Data Science. It covers a broad range of methodologies for working with and making informed decisions based on real-world data. Core topics introduced in this course include basic statistics, data exploration, data cleaning, data visualization, business intelligence, and data analysis. Students will utilize various techniques and tools to explore, understand and visualize real-world data sets from various domains and learn how to communicate data results to decision makers.
Cat I (offered at least 1x per Year). This course focuses on model- and data-driven approaches in Data Science. It covers methods from applied statistics (regression), optimization, and machine learning to analyze and make predictions and inferences from real-world data sets. Topics introduced in this course include basic statistics (regression), analytics (explanatory and predictive), basics of machine learning (classification and clustering), eigen values and singular matrices, data exploration, data cleaning, data visualization, and business intelligence. Students will utilize various techniques and tools to explore and understand real-world data sets from various domains.
Cat I (offered at least 1x per Year). This course introduces core methods in Data Science. It covers a broad range of methodologies for working with large and/or high-dimensional data sets to making informed decisions based on real-world data. Core topics introduced in this course include data collection through use cycle, data management of large-scale data, cloud computing, machine learning and deep learning. Students will acquire experience with big data problems through hands-on projects using real-world data sets.
Cat. I This course introduces the emerging techniques and infrastructures for big data management and analytics including parallel and distributed database systems, map-reduce, Spark, and NO-SQL infrastructures, data stream processing systems, scalable analytics and mining, and cloud-based computing. Query processing and optimization, access methods, and storage layouts developed on these infrastructures will be covered. Students are expected to engage in hands-on projects using one or more of these technologies. Recommended background: Knowledge in database systems at the level of CS4432, and programming experience are assumed.
Introduction to Data Science provides an overview of Data Science, covering a broad selection of key challenges in and methodologies for working with big data. Topics to be covered include data collection, integration, management, modeling, analysis, visualization, prediction and informed decision making, as well as data security and data privacy. This introductory course is integrative across the core disciplines of Data Science, including databases, data warehousing, statistics, data mining, data visualization, high performance computing, cloud computing, and business intelligence. Professional skills, such as communication, presentation, and storytelling with data, will be fostered. Students will acquire a working knowledge of data science through hands-on projects and case studies in a variety of business, engineering, social sciences, or life sciences domains. Issues of ethics, leadership, and teamwork are highlighted.
This course surveys the statistical methods most useful in data science applications. Topics covered include predictive modeling methods, including multiple linear regression, and time series; data dimension reduction; Discrimination and classification methods, clustering methods;and committee methods. Students will implement these methods using statistical software.
Prerequisites: Statistics at the level of MA 2611 and MA2612 and linear algebra at the level of MA 2071.
Emerging applications in science and engineering disciplines generate and collect data at unprecedented speed, scale, and complexity that need to be managed and analyzed efficiently. This course introduces the emerging techniques and infrastructures developed for big data management including parallel and distributed database systems, map-reduce infrastructures, scalable platforms for complex data types, stream processing systems, and cloud-based computing. Query processing, optimization, access methods, storage layouts, and energy
management techniques developed on these infrastructures will be covered. Students are expected to engage in hands-on projects using one or more of these technologies. Prerequisites: A beginning course in databases at the level of CS4432 or equivalent knowledge, and programming experience.
Innovation and discoveries are no longer hindered by the ability to collect data, but the ability to summarize, analyze, and discover knowledge from the collected data in a scalable fashion. This course covers computational techniques and algorithms for analyzing and mining patterns in large-scale datasets. Techniques studied address data analysis issues related to data volume (scalable and distributed analysis), data velocity (high-speed data streams), data variety
(complex, heterogeneous, or unstructured data), and data veracity (data uncertainty). Techniques include mining and machine learning techniques for complex data types, and scaleup and scale-out strategies that leverage big data infrastructures. Real-world applications using these techniques, for instance social media analysis and scientific data mining, are selectively discussed. Students are expected to engage in hands-on projects using one or more of these technologies. Prerequisites: A beginning course in databases and a beginning course in data
mining, or equivalent knowledge, and programming experience.
The foci of this class are the essential statistics and linear algebra skills required for Data Science students. The class builds the foundation for theoretical and computational abilities of the students to analyze high dimensional data sets. Topics covered include Bayes’ theorem, the central limit theorem, hypothesis testing, linear equations, linear transformations, matrix algebra, eigenvalues and eigenvectors, and sampling techniques, including Bootstrap and Markov chain Monte Carlo. Students will use these techniques while engaging in hands-on projects with real data.
Prerequisites: Some knowledge of integral and differential calculus is recommended.
This course will offer a mathematical and practical perspective on artificial neural networks for machine learning. Students will learn about the most prominent network architectures including multi-layer feedforward neural networks, convolutional neural networks (CNNs), auto-encoders, recurrent neural networks (RNNs), and generative-adversarial networks (GANs). This course will also teach students optimization and regularization techniques used to train them -- such as back-propagation, stochastic gradient descent, dropout, pooling, and batch normalization. Connections to related machine learning techniques and algorithms, such as probabilistic graphical models, will be explored. In addition to understanding the mathematics behind deep learning, students will also engage in hands-on course projects. Students will have the opportunity to train neural networks for a wide range of applications, such as object detection, facial expression recognition, handwriting analysis, and natural language processing.
Prerequisite: Machine Learning (CS 539), and knowledge of Linear Algebra (such as MA 2071) and Algorithms (such as CS 2223).
This course introduces the theory, design, and implementation of text-based and Web-based information retrieval systems. Students learn the key concepts and models relevant to information retrieval and natural language processing on largescale corpus such as the Web and social systems. Topics include vector space model, crawling, indexing, web search, ranking, recommender systems, embedding and language model. Prerequisites: statistical learning at the level of DS 502/MA 543 and programming skills at the level of CS 5007.
Reinforcement Learning is an area of machine learning concerned with how agents take actions in an environment with a goal of maximizing some notion of cumulative reward. The problem, due to its generality, is studied in many disciplines, and applied in many domains, including robotics and industrial automation, marketing, education and training, health and medicine, text, speech, dialog systems, finance, among many others. In this course, we will cover topics including: Markov decision processes, reinforcement learning algorithms, value function approximation, actor-critics, policy gradient methods, representations for reinforcement learning (including deep learning), and inverse reinforcement learning. The course project(s) will require the implementation and application of many of the algorithms discussed in class.
Machine Learning has proven immensely effective in a diverse set of applications. This trend has reached a new high with the application of Deep Learning virtually in any application domain. This course studies the applications of Machine Learning in the sub domain of Cybersecurity by introducing a plethora of case studies including anomaly detection in networks and computing, side-channel analysis, user authentication and biometrics etc. These case studies are discussed in detail in class, and further examples of potential applications of Machine Learning techniques including Deep Learning are outlined. The course has a strong hands-on component, i.e. students are given datasets of specific security applications and are required to perform simulations.
The internship is an elective-credit option designed to provide an opportunity to put into practice the principles studied in previous Data Science courses. Internships will be tailored to the specific interests of the student. Each internship must be carried out in cooperation with a sponsoring organization, generally from off campus and must be approved and advised by a core faculty member in the Data Science program. The internship must include proposal, design and documentation phases. Following the internship, the student will report on his or her internship activities in a mode outlined by the supervising faculty member. Students are limited to counting a maximum of 3 internship credits towards their degree requirements for the M.S. degree in Data Science. We expect a full-time graduate student to take on only part-time (20 hours or less of) internship work during the regular academic semester, while a full-time internship of 40 hours per week is appropriate during the summer semester as long as the student does not take a full class load at the same time. Internship credit cannot be used towards a certificate degree in Data Science. The internship may not be completed at the students current place of employment.
Special Topics in Data Science is course offering that will cover a topic of current interest in detail. This serves as a flexible vehicle to provide a one-time offering of topics of current interest as well as to offer new topics before they are made into a permanent course.
Directed Research study, conducted under the guidance of a faculty member affiliated with the Data Science Program, investigates the challenges and techniques central to data science, and aims to develop novel approaches and techniques towards solving these challenges. The student who chooses this course must produce a written report to fulfil the course requirement.
This 3-credit graduate qualifying project, done in teams, can be taken a second time for credit with permission by the instructor, up to a total of 6 credits. The project is to be carried out in cooperation with a sponsor or industrial partner. It must be overseen by a faculty member affiliated with the Data Science Program. This offering integrates theory and practice of Data Science, and includes the utilization of tools and techniques acquired in the Data Science Program. In addition to a written report, this project must be presented in a formal presentation to faculty of the Data Science program and sponsors. Professional development skills, such as communication, teamwork, leadership, and collaboration, along with storytelling, will be practiced.
The Masters Thesis in Data Science consists of a research and development project worth a minimum of 9 graduate credit hours and is advised by a faculty member affiliated with the Data Science Program. A thesis proposal must be approved by the DS Program Review Board and the students advisor, before the student can register for more than three thesis credits. The student must satisfactorily complete a written thesis document, and present the results to the DS faculty in a public presentation.