CALL 17-2019-1 - PhD Fellowship in ‘Machine and Deep Learning for Massive MIMO in Beyond 5G and 6G Communication Systems’
The Communications System Division of the CTTC is looking for candidates interested in pursuing a PhD in its Advanced Signal and Information Processing Department. The contract will be funded by the Spanish Government (MICINN, Ministry of Science, Innovation, and Universities) under its prestigious call ‘Contratos para la Formación de Doctores’. For this year’s call, a PhD fellowship has been pre-allocated to CTTC to carry out research in the context of the on-going project ARISTIDES (Statistical Learning and Inference for Large Dimensional Communication Systems, ref. RTI2018-099722-B-I00). Motivated candidates are sought for this position.
Machine learning (ML) techniques have been known for a long time as powerful tools for classification and regression (prediction) problems. More recently, deep learning (DL) has emerged with more advanced tools capable of building universal classifiers and/or approximate general functions. Both ML and DL have been successfully applied to a number of areas including image restoration and identification, natural language processing, or network security, to name a few.
At present time, it is generally agreed that Artificial Intelligence (AI) in general, and ML and DL in particular, are called to play a pivotal role in the design of the (increasingly complex) beyond 5G and 6G communication systems that will take place in the 2020-2030 period. To date, however, most of the applications of ML/DL techniques to communication problems have been confined to the area of wireless network optimization (resource or spectrum management, cell association, or selection of radio access technologies, to name a few). More recently, using ML/DL techniques for problems and functionalities related with the physical layer of communication systems (e.g., coding, modulation, detection, equalization, pre-coding, among others) has started attracting lots of attention from the research community.
This PhD thesis will revolve around the application of ML/DL tools to the design of large-dimensional antenna systems for beyond 5G and 6G networks. Specifically, the advent of communication systems operating in the millimetre wave band largely facilitates the implementation of transceivers with a large number of antennas (i.e., massive MIMO). Despite that in MIMO precoding optimal algorithms exist, learning-based methods can, on the one hand, significantly reduce computational complexity and, on the other, are better suited to learn a number of non-linear features of such systems which are not easy to model with traditional engineering (vs. data-driven) approaches. Along the same lines, many beam selection/alignment, or antenna selection problems can be reformulated as multi-class classification problems and, thus, be efficiently solved with learning-based methodologies. A related (and, to a large extent, unexplored) problem to be addressed is that of user clustering for large (distributed) antenna systems. This problem, again, is amenable to be solved with data-driven approaches (e.g., kernel-based learning methods) along with selected tools from optimization theory. In addressing the aforementioned problems, particular attention will be paid to assess (i) the inherent complexity vs. performance trade-offs of the proposed techniques; (ii) their robustness w.r.t. imperfect channel state information or mismatches between the assumed and actual channel or system models (e.g., linear or not); and (iii) their scalability in the number of antenna elements or user terminals.
QUALIFICATIONS AND EXPERIENCE
We are looking for highly-motivated candidates, with a strong desire to learn and interest in performing cutting edge research in a truly international R&D center with a very high involvement in Horizon 2020 (European) projects. Prerequisites for this PhD position are:
- Master’s degree in telecommunications, electronic/electrical engineering or in related fields.
- Strong mathematical/analytical skills and problem solving capabilities.
- Solid academic record.
- Fluency in English (both written and oral)
Preference will be given to candidates with:
- Strong Python, Matlab or Octave programming skills.
- Knowledge in machine/deep learning techniques.
- Experience in working with Tensorflow, Keras and Machine Learning libraries (e.g. SciKit Learn).
- Experience in using GPU technology
The duration of the contract is 4 years, starting in Q4/2019-Q1/2020. The selected candidates will prepare their application in collaboration with CTTC for submission to the FPI-2019 call (estimated deadline: October 2019). For further details on the terms and conditions of this call, please, see the documentation of the last call issued here.
Researchers interested in applying for this position should send their curriculum vitae, academic record, and the names and addresses of at least two referees to this online application. Application deadline for candidates is 27th September 2019.
Contact person: Dr. Carles Antón Haro, Director of R&D Programs, Senior Research Associate (http://www.cttc.es/people/canton )
The Centre Tecnològic de Telecomunicacions de Catalunya (CTTC), in Castelldefels – Barcelona, is a growing and well-funded research institution fostering excellence and diversity. CTTC offers a highly international environment at an attractive location. As a research centre, CTTC provides a fertile environment for research cooperation and innovation between different disciplines.
CTTC seeks to increase the number of women in those areas where they are underrepresented and therefore explicitly encourages women to apply.
CTTC is committed to increasing the number of individuals with disabilities in its workforce and therefore encourages applications from such qualified individuals.