|
|
Course Criteria
Add courses to your favorites to save, share, and find your best transfer school.
-
3.00 Credits
University of Massachusetts Amherst has not provided a description for this course
-
1.00 Credits
This course will cover recent advances in big data systems, an increasingly important and challenging area that deals with the processing and analysis of extremely large amounts of data. We will present and discuss recent research papers in big data systems coupled with a project involving one of several real-life large-scale datasets crawled from a variety of online sources. The projects will enable students to familiarize themselves with tools and platforms such as Hadoop, EC2, etc. as well as adaptation of data mining algorithms so as to meet the challenges of data analysis at scale. The class may optionally be taken for 1 credit without the project option.
-
3.00 Credits
This course will provide an overview of the key ideas that underlie the Bayesian approach to modeling data, with a particular focus on text. The course will primarily consist of discussing, deriving, and implementing a number of Bayesian models of text (and their associated inference algorithms) in order to understand their fundamental strengths and weaknesses, as well as explore the relationships between them. The aim of the course is to develop the knowledge and skills needed to design, implement, and apply such models to real-world data. Students entering the course should have good programming skills, knowledge of algorithms, knowledge of probability, statistics, or machine learning, and a strong interest in text analysis. To facilitate productive discussion, students with diverse research backgrounds and interests are especially encouraged to participate.
-
3.00 Credits
This course introduces graduate students to basic ideas about conducting a personal research program. Students will learn basic methods for activities such as reading technical papers, selecting research topics, devising research questions, planning research, analyzing experimental results, modeling and simulating computational phenomena, and synthesizing broader theories. The course will be structured around three activities: lectures on basic concepts of research strategy and techniques, discussions of technical papers, and preparation and review of written assignments. Significant reading, reviewing, and writing will be required, and students will be expected to participate actively in class discussions.
-
3.00 Credits
In recent years, the ability to continuously monitor activities, health, and lifestyles of individuals using sensor technologies has reached unprecedented levels. Wearable "on-body" sensors now enable routine and continuous monitoring of a host of physiological signals (e.g., heart rate, blood pressure, respiratory rate, blood glucose, etc.), physical activity (e.g. calorie expenditure), and sleep patterns (e.g. REM vs deep sleep). In addition, the typical smartphone comes routinely equipped with a plethora of sensors for monitoring both activity and location, enabling (in combination with other sensors) higher-order inferences about more complex human activities/behavioral states (e.g., stress, addiction, etc.). Such ubiquitous sensing in daily life, referred to as mobile health, promises to revolutionize our understanding of the varied social, environmental, and behavioral context (and potentially determinants) of a wide range of human activities and health conditions. This course is an exploration of challenges in mobile health including: a) practical considerations including energy-efficiency, interruptions, wearability, privacy, etc. b) inference of key health assessments from sensor data including stress, mood, eating behavior, sleep patterns, calorie intake and expenditure, mental health, etc. c) personalized health assessment by combining continuous mobile sensor data using a variety of on-body sensors (chestband, wristband, smartphone) d) novel interventions that can take advantage of these models to elicit changes in health behavior. Students from diverse research backgrounds/interests are encouraged to attend for more productive discussion. The course will consist of reading, presenting, and discussing papers, and working with on-body sensors and/or datasets as appropriate. We will also have guest lectures that you are expected to attend. Students taking the class for 3 credits will be expected to define and execute a semester-long research project. Those interested in doing hands-on projects will be given access to Google Nexus Prime smartphones, Zephyr Bioharness chestbands with EKG, respiration, skin conductance, and accelerometer sensors, and wristbands that can sense activity patterns. Students interested in data analytics will have access to several datasets.
-
1.00 Credits
This graduate seminar course will cover recent developments in programming languages and systems, examining the latest research papers from top programming languages and systems conferences. Topics of interest include bug detection and correction, domain-specific languages, and emerging topics like concurrency on multicore architectures.
-
3.00 Credits
We will introduce neural networks and modeling of brain functions: the inspiration, engineering applications, theoretical analysis, as well as psychological and biological modeling. We will review different neural networks within the two groups: Feed forward networks, applications, and approximation theorem; Recurrent neural networks and computational power; We will also focus on supervised and unsupervised learning with applications in clustering; representability; and Models of memory, diseases, and healthy perception.
-
3.00 Credits
This seminar examines recent work in explanatory and tutoring systems. Participants study artificial intelligence in education, a young field that explores theories about learning, and explores how to build software that delivers differential teaching as it adapt its response to student needs and domain knowledge. Such software supports people who work alone or in collaborative inquiry, students who question their own knowledge, and students who rapidly access and integrate global information. This course describes how to build these tutors and how to produce the best possible learning environment, whether for classroom instruction or lifelong learning. The objective of the course is to stimulate awareness of research issues and to promote sound analytic and design skills as they pertain to building knowledge representations and control strategies. Specific topics include collaboration, inquiry, dialogue systems, machine learning, simulators, authoring tools and user models. The course is appropriate for students from many disciplines (computer science, linguistics, education, and psychology), researchers, and practitioners from academia, industry, and government. No programming is required. Students read and critique tools, methods, and ideas, learn how artificial intelligence is applied (e.g., vision, natural language), and study the complexity of human learning through advances in cognitive science.
-
3.00 Credits
This is a research course in statistics of networks and graphs. Topics will be wide-ranging, including models for cross-sectional and dynamic networks, partially-observed networks, and networks with latent structures. Also included are network sampling, non-parametric statistical methods for networks, and data stream methods for graphs. Course discussion will highlight comparisons across frameworks for statistical analysis of networks, as well as across application areas. Classes will require reading research articles before class, listening to presentations of the articles, and discussing them. Students will be responsible for in-class presentations of at least one article over the semester. This course is offered for either one or three credits. In addition to class participation as described above, students enrolled for 3 credits will be responsible for completing a course project.
-
1.00 Credits
The "smart grid" uses computing and communication technologies to enhance the efficiency, reliability, sustainability and flexibility of the generation, distribution and use of electricity. This seminar will introduce participants to the grid and to the smart grid, and will read current smart grid research papers. Topics will include smart grid communication protocols, security and privacy, smart grid monitoring and measurement, demand response, storage, intermittent generation (e.g., renewable sources), smart homes and building and smart grid modeling. This seminar is being offered jointly and collaboratively at The University of Massachusetts Amherst and at The Indian Institute of Technology Bombay. Students may register for 1 credit or 3 credits. Students registering for a single credit will be expected to make a class presentation (developed in consultation with one of the professors) and to actively participate in class discussions. Students registering for 3 credits will also define and complete a research project on a topic of interest, in consultation with the course professors. Projects involving students from both UMass and IITB are particularly encouraged. Pre-requisites: Graduate student status or permission of the instructors. An undergraduate course in operating systems and/or computer networks is required.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|