Ph.D. position in Wireless Neuro-inspired Artificial Intelligence

With main drivers the privacy risks and power constraints, future large scale ultra dense sensor deployments 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 prevent data leaks to more centralized points, simplify wireless tranceivers (hence power consumption) and use non-explicit cues for inference within the context and environment of data sources.

TU/e , as part of a large multinational european consortium DAIS , will investigate novel ways to use non-linearities in wireless medium, tranceivers and transmissions to simultaneously enable communication and computation. The project, Distributed Artificial Intelligent System (DAIS - G.A. 101007273), was funded by the ECSEL Joint Undertaking (ECSEL JU) and a multitude of countries: Sweden, Netherlands, Germany, Spain, Denmark, Norway, Portugal, Belgium, Slovenia, Czech Republic, Turkey.

DAIS aims, besides others, at:

• providing intelligent processing and communication locally at the edge to enable real-time and safety-critical industrial applications, and
• distributing and dividing the complex AI operations between the cloud and edge, with edge undertaking early intelligent data processing reducing the bandwidth of data being transmitted to cloud.

TU/e envisions low-power wireless meshes as swarms of computing and communication units able to collectively approximate any non-linear function. 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 medium 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 network management and control 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 DAIS' 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.