Ph.D. position in Over-the-air Distributed Computing

The Advanced Network Management and Control laboratory at Electrical Engineering (EE) department of TU/e has one Ph.D. position in the field of wireless communications, distributed computing and distributed AI.

Goal and background

Isolated edge networks, like orbiting satellite swarms or sensing swarms in earth cavities, are large scale ultra dense wireless sensor deployments which open new fields for distributed AI. Novel AI mechanisms need to simultaneously execute processing and communication at the wireless edge meshes. They are expected to reduce the large data volumes to be either stored or transmitted to more centralized points.

TU/e is leading a Dutch consortium, Autonomous Distribution Architecture on Progressing Topologies and Optimization of Resources (ADAPTOR), which investigates novel ways to use non-linearities in wireless medium, tranceivers and transmissions to simultaneously enable communication and computation. The project was funded by the Dutch Organisation for Scientific Research (NWO) and Thermo Fisher Scientific in cooperation with ASTRON.

ADAPTOR aims, besides others, at providing intelligent computing and communication strategies locally at micro-satellite swarms to minimize the data volumes to be transferred to Earth. Several maintenance and functional services need to be computed completing at runtime a multitude of non-linear approximations. Yet, the scarcity of resources (compute, storage and communication) at those distributed instruments require novel computing approaches.

Research Challenges

TU/e envisions low-power wireless meshes as swarms of computing and communication units able to approximate several non-linear functions collectively and simultaneously. Instead of packing more capacity per device or link, we will study novel AI paradigms which simultaneously harvest both the complexity of neural networks and their environment they operate in. This allows transforming input data to a hyper dimensional space at a lower power consumption.

Role

The candidate will analytically and experimentally study the transformative power of the wireless transmissions and channel conditions on wirelessly distributed neural networks. Should this be well understood, the next step is to devise ways to use and control this power to improve the processing capabilities of wireless meshes. This work sits at the intersection of wireless communications and artificial intelligence involving embedded systems, signal processing, advanced networking, recurrent and spiking neural networks.

Work environment

Eindhoven University of Technology (TU/e) is one of Europe's top technological universities, in the heart of one of Europe's largest high-tech innovation ecosystems - the Eindhoven Brainport region. Research at TU/e is a combination of academic excellence and a strong real-world impact through close collaboration with regional and international high-tech industries.

The candidate will be employed within the Electro-Optical Communications Group (ECO), in particular within the advanced networking laboratory . The candidate will strongly interact with the ECO group, which consists of over 70 researchers. This position is embedded within the Center for Wireless Technology (CWT/e) at TU/e which focuses on four programs: Ultra-High Data-Rate Systems, Ultra-Low Power and Internet-of-Things Communication, Terahertz Technology, and Radio Astronomy.

We are looking, therefore, for one strong Ph.D. researcher to:
Collaboration - Continuously interact with other ECO researchers and with ADAPTOR's partners and other users.
Dissemination - Contribute to the project reporting, scientific publications and other activities related to the preparation of new grant proposals to national and European projects.