Multimodal Data Fusion for Next Generation Wireless Networks
19 Octobre 2021
Catégorie : Doctorant
Position: PhD / CIFRE
Institution: Advanced Wireless Technology Labs, Huawei Paris Research Centre, and EURECOM, Sophia Antipolis
Communication between intelligent machines is expected to be a major aspect of future wireless networks. While current networks are designed to support the needs of humans, communication between machines exhibits largely different protocols and requirements. The design of mechanisms and networking for such communication lies in the intersection of multimodal representation learning, wireless networks, and semantic communications.
Data fusion is a specific scenario and application within the general picture of communication between intelligent machines. Devices observe and process local data, and communicate this over a joint wireless channel to a centre that fuses this data. The time-varying and resource-limited wireless channel imposes specific constraints and challenges on the design and operation of such a system. On the other hand, goal orientation and semantic aspects allow for and demand specific optimisation.
The presence of multiple modalities, including vision data, sensor data, and sequential data, has the potential to offer additional information that models can exploit to build richer representations. Key challenges revolve particularly around two points: first the methodology to infer a joint multimodal representation that exploits the available synergies and obtains a gain in terms of representation compared to a unimodal model; and second the methodology to efficiently communicate over the wireless channel, given its particularly characteristics, to obtain and use such a model to perform the various tasks required.
The applicant is expected to have the following skills:
- Theoretical and practical knowledge in machine learning, particularly deep learning and representation learning
- Mathematical knowledge in statistics, topology, logic, category theory (desirable)
- Knowledge in communication theory, wireless transmission( desirable)
- Analytical skills, creativity and methodological approach for problem solving
- Programming skills in Python and DL tools
- Master in computer science, engineering, or equivalent
- Interest and ability to work in international teams
- Fluency in spoken and written English
The position is open now. Please send your full CV and motivation letter, transcripts, and contact information for two references or letters of reference to email@example.com. The application should be in English language.
For questions on the topic or the position, you may contact Dr Ingmar Land, Huawei Paris Research Centre, by email to firstname.lastname@example.org, or Professor Pietro Michiardi, Eurecom, by email to email@example.com.