- PhD. Scalable Real-time Computations for Video Data Analytics
- University Graduate
FTE: 1 - 1
Job descriptionVideo data is dominating the Internet traffic nowadays. Video data analytics has become a powerful tool for many emerging applications such as smart cities and autonomous driving in the Internet-of-Things (IoT) era. Nowadays, deep learning has become the standard approach for video data analytics due to its high analytics accuracy. However, deep learning algorithms are typically computation intensive and require the support of powerful computing infrastructures such as those based on GPUs, TPUs, or other accelerators. This development poses challenges towards efficient video data analytics, especially for real-time applications.
This PhD project will focus on building an efficient and scalable computing system for video data analytics by enabling the self-adaptive execution of video data analytics applications. The project is part of a larger program together with the Intelligent Sensory Information Systems Lab of the University of Amsterdam and with Amsterdam Schiphol Airport. First, a self-adaptive architecture will be developed to allow a deep learning model to conduct tradeoffs between latency and accuracy at runtime. Second, the semantics of the video data analytics application will be analyzed as a whole and a strategy will be designed to coordinate the adaptation decisions for different models in the same application to achieve the best application-level performance. Finally, a distributed environment will be considered where the network communication between models deployed on different places is taken into account in the adaptation coordination strategy. The resulting system will be tested with popular video data analytics applications on a cluster such as our DAS-6.
The PhD will work with other PhDs in a multi-disciplinary team with experts on computer systems, networking, and deep learning. In addition, the PhD will interact with experts on computer vision from the University of Amsterdam and with Schiphol Airport.
- analyze the literature to understand the state-of-the-art in deep learning model adaptation
- design a new model architecture to allow for self-adaptation
- conduct semantics analysis of modern applications that are based on multiple video analytics models
- develop a coordination strategy for application-level model adaptation
- explore the limitations of the coordination strategy when deployed in a distributed environment
- design a network-aware coordination strategy for application-level model adaptation
- implement the system and build a prototype
- a Master's degree in Computer Science, Computational Science or related field
- a background in video stream analytics or deep learning in general
- excellent programming skills (e.g., C++, Python) and deep systems/network programing experience
- strong collaboration and communication skills
What are we offering?A challenging position in a socially involved organization. The salary will be in accordance with university regulations for academic personnel and amounts €2,395 (PhD) per month during the first year and increases to €3,061 (PhD) per month during the fourth year, based on a full-time employment. The job profile: is based on the university job ranking system and is vacant for at least 1 FTE.
The appointment will initially be for 1 year. After a satisfactory evaluation of the initial appointment, the contract will be extended for a duration of 4 years.
Additionally, Vrije Universiteit Amsterdam offers excellent fringe benefits and various schemes and regulations to promote a good work/life balance, such as:
- a maximum of 41 days of annual leave based on full-time employment
- 8% holiday allowance
- 8.3% end-of-year bonus
- Contribution to commuting expenses
- A wide range of sports facilities which staff may use at a modest charge
About Vrije Universiteit AmsterdamThe ambition of Vrije Universiteit Amsterdam is clear: to contribute to a better world through outstanding education and ground-breaking research. We strive to be a university where personal development and commitment to society play a leading role. A university where people from different disciplines and backgrounds collaborate to achieve innovations and to generate new knowledge. Our teaching and research encompass the entire spectrum of academic endeavour – from the humanities, the social sciences and the natural sciences through to the life sciences and the medical sciences.
Vrije Universiteit Amsterdam is home to more than 26,000 students. We employ over 4,600 individuals. The VU campus is easily accessible and located in the heart of Amsterdam’s Zuidas district, a truly inspiring environment for teaching and research.
We are an inclusive university community. Diversity is one of our most important values. We believe that engaging in international activities and welcoming students and staff from a wide variety of backgrounds enhances the quality of our education and research. We are always looking for people who can enrich our world with their own unique perspectives and experiences.
The Faculty of Science
The Faculty of Science inspires researchers and students to find sustainable solutions for complex societal issues. From forest fires to big data, from obesity to medicines and from molecules to the moon: our teaching and research programmes cover the full spectrum of the natural sciences. We share knowledge and experience with leading research institutes and industries, both here in the Netherlands and abroad.
Working at the Faculty of Science means working with students, PhD candidates and researchers, all with a clear focus on their field and a broad view of the world. We employ more than 1,250 staff members, and we are home to around 6,000 students.
About the department, institute, project
The department of Computer Science has approximately 170 staff members, including 35 tenured staff and 40-50 PhD students. Much of the research with the department is embedded in the Network Institute of Vrije Universiteit, covering beyond Computer Science and Artificial Intelligence disciplines such as Social Sciences, Humanities, and Economics. The Department also actively participates in Amsterdam Data Science, a collaboration between more than 600 data science researchers from different institutions in Amsterdam.
This position fills a vacant role in the High Performance Distributed Computing group, which has decades of research experience with programming environments for large-scale distributed systems.
ApplicationAre you interested in this position? Please apply via the application button and upload your curriculum vitae and cover letter until July 23, 2020.
Applications received by e-mail will not be processed.
If you have any questions regarding this vacancy, you may contact:
Name: Prof. Dr. Henri Bal
Position: Full Professor
No agencies Meer informatie en solliciteren