Ongeveer 14 uur geleden - Universiteit van Tilburg - Den Bosch
The goal of this project is to develop algorithms that analyze videoclips of human movement in sports (e.g. sprinting, jumping, kicking a ball in soccer), eval…
In the context of the joint research project between TU Eindhoven and KPN we have one 4-year PhD student position in the Data Mining group at the Department of Computer Science, TU/e Eindhoven.
Development of intelligent applications running advanced machine learning models on the edge of the network such as mobile, smart home, internet-of-things platforms require connectivity and computing resources. As the complexity of the applications grow (i.e. streaming video processing, virtual/augmented reality, mobile solutions) the computer network infrastructure between the point of service and the compute infrastructure is becoming a bottleneck. With the advancements of hardware at the edge of the network, where the actual service is needed, the possibility to move some or most of the computational load is becoming evident.
Thus, we aim to study methods for extending deep neural network models from the core of the network into models that exist both on the edge and on the core. The main practical goal is formulated as: taking into account network factors such as available resource on the edge, connectivity, bandwidth, latency and jitter, provide reliable, efficient and scalable Deep Learning based solutions to a multitude of connected devices. To achieve this goal, we will study the issues of DLCE reliability, efficiency, scalability and improved experience.
This project is in collaboration with KPN, a Dutch landline and mobile telecommunications company. DLCE is part of a larger project TU/e-KPN flagship SmartONE, which constitutes an interdisciplinary collaboration between KPN and 4 TU/e research centers: Smart Cities, Wireless Technology, Photonics Institute and Data Science.
We are looking for candidates that meet the following requirements: