A classical problem in causal inference is that of matching treatment units to control units in an observational dataset. This problem is distinct from simple estimation of treatment effects as it provides additional practical interpretability of the underlying causal mechanisms that is not available without matching.
Hosted at Duke University and bringing together researchers, students and industry labs for a day of technical talks and posters in the broad areas of privacy, security, cryptography, and blockchains, the first-ever Triangle Area Privacy and Security Day (TAPS) is modeled after similar events occurring in Boston, DC and New York. The program will feature technical talks and a poster session.
Students are invited to meet with Adam Cue ‘13, a Duke CS graduate whose father, Eddy Cue, is also a Duke CS alum and currently a Senior Vice President at Apple.
Adam is a co-founder of Aspen Designs Inc, a creative collective committed to transforming teamwork with their Navigator software. After 18 months of hard work and thousands of conversations, Navigator launched this summer, and is now available on iOS.
Pattern mining is a core area in data mining. In this talk, I will review my work on pattern mining in the last 20 years. I will focus on three interleaving main lines, technical principles, data variety, and new application challenges. I will illustrate how the advances in pattern mining empower new progress in some other areas, such as data warehouses, information retrieval, and network science. Moreover, I will demonstrate how pattern mining research produced visible impact on industrial practice.
Come join your fellow alumni, faculty and staff from the Computer Science Department during Friday afternoon’s homecoming.
This year's event will feature remarks by distinguished alumnus Vijay Srinivasan '95. Srinivasan previously worked with Professor Gershon Kedem, and is now the CEO of Willow TV International.
Connect and celebrate with your classmates at this casual, fun reunion reception. There will be a variety of food served, and an open wine and beer bar will be available.
Join Vijay Srinivasan, the founder and CEO of Willow TV, American Cricket Enterprises partner, and investor in USA Cricket. He will will hold an informal meet and greet with students here at Duke and share his story about progressing from a graduate student to a cricket focused media mogul. Students: this talk is for you, if you're interested in computer science or want to pursue a career in media and sports and entertainment.
Video games, Virtual Reality (VR), Augmented Reality (AR), and Smart appliances (e.g., smart TVs and drones) all all for a new way for users to interact and control them. Motivated by this observation, we have developed a series of novel motion tracking technologies using acoustic signals. A unique feature of our approach is that it can achieve mm-level tracking accuracy on smartphones without special hardware. We further develop a few interesting applications on top of our motion tracking technology such as a follow-me drone and acoustic imaging on mobile phones.
As software moves off the desktop and into data centers, and cell phones use server requests as the other half of apps, the observation tools for large-scale distributed transaction systems are not keeping up with the complexity of the environment. Exploring a simpler environment can help expose some of the problems that confront today’s tool users and tool builders. There is a lot to be learned from careful observation of a program and its complete surrounding context, even one as trivial as “Hello, World!”.
InDuke TechConnect brings students and employers together for networking and education. Each year, employers connect with Engineering and Computer Science students in an open, dynamic networking environment. Students come prepared with resumes to meet industry and tech representatives to learn about employment opportunities available, the characteristics employers seek as well as a realistic and insightful view of the job market and career paths for students interested in engineering and technical careers.
CS Department, please join us for this special opportunity to come together in fellowship and welcome our newest faculty, graduate students, undergraduate students, postdocs, and staff.
- Meeting: 4:30pm
- Dinner: 5:15pm - Families, please join us for dinner @ 5:15 pm.
Entertainment will be provided for children, and free parking is available at the Washington Duke Inn. Contact Pam Spencer with any questions. We hope to see you there.
The second annual Triangle Machine Learning Day is hosted by SAMSI at Duke University's Penn Pavilion. This event brings together researchers and applied scientists in different areas of machine learning, including industrial applications, academic theory, and everything in between, for a day of technical talks and posters.
We establish first a theoretical foundation for the use of Gromov-Hausdorff (GH) distance for point set registration with homeomorphic deformation maps perturbed by Gaussian noise. We then present a probabilistic, deformable registration framework. At the core of the framework is a highly efficient iterative algorithm with guaranteed convergence to a local minimum of the GH-based objective function. The framework has two other key components – a multi-scale stochastic shape descriptor and a data compression scheme.
Machine learning is accelerating the translation of biological and biomedical data to advance the detection, diagnosis, treatment, and prevention of diseases. However, the unprecedented scale and complexity of large-scale biomedical data have presented critical computational bottlenecks requiring new concepts and enabling tools.
- Luis von Ahn's goals, vision, and ideas along with captivating stories.
- Past, Present, and Future of learning and translation.
- Why students might consider work at an established startup, a new startup, or not at a startup.
- For students: how to think about what you'll do at Duolingo or elsewhere after graduating.
There will be a reception at 5:30pm after the talk in the Hall of Science.
A core problem in statistics and machine learning is to approximate difficult-to-compute probability distributions. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation about a conditional distribution. In this talk I review and discuss innovations in variational inference (VI), a method a that approximates probability distributions through optimization. VI has been used in myriad applications in machine learning and Bayesian statistics.
This talk will present our contributions in the domain of field-hardened resilient robotic autonomy and specifically on multi-modal sensing-degraded GPS-denied localization and mapping, informative path planning, and robust control to facilitate reliable access, exploration, mapping and search of challenging environments such as subterranean settings.
There are multi-robot motion planning (MRMP) problems involving dozens of robots, which can be speedily solved, while other are practically unsolvable. What makes an MRMP problem easy or hard? In the first part of the talk I'll describe our quest to resolve this issue, and some progress we have made in the context of unlabeled MRMP.