Marie Skłodowska-Curie Actions

MSCA-PF: Joint application at the University of Granada. Department of Computer Languages and Systems and Software Engineering

    26/10/2021 18:30 - Europe/Brussels
    HE / MSCA
    Spain, Granada
    International Research Projects Office
    Promotion and Advisory Unit

Professor Manuel I. Capel from the Department of Computer Languages and Systems and Software Engineering at the University of Granada, welcomes postdoctoral candidates interested in applying for a Marie Skłodowska-Curie Postdoctoral Fellowships (MSCA-PF) in 2021 at this University. Please note that applicants must comply with the Mobility Rule (more information about the 2020 call: http://sl.ugr.es/0aNV, the 2021 call is not yet open).

Brief description of the institution:

The University of Granada (UGR), founded in 1531, is one of the largest and most important universities in Spain. With over 60.000 undergraduate and postgraduate students and 6.000 staff. UGR offers a total of 89 degrees, 110 master’s degrees and 28 doctoral programmes through its 123 departments and 27 centers. Consequently, the UGR offers one of the most extensive and diverse ranges of higher education programmes in Spain.

The UGR has awarded with the "Human Resources Excellence in Research (HRS4R)", which reflects the UGR’s commitment to continuously improve its human resource policies in line with the European Charter for Researchers and the Code of Conduct for the Recruitment of Researchers. UGR is also a leading institution in research, located in the top of Spanish universities by a variety of ranking criteria, such as national R&D projects, fellowships awarded, publications, or international funding. UGR is one of the few Spanish Universities listed in the Shanghai Top 500 ranking - Academic Ranking of World Universities (ARWU) (http://sl.ugr.es/0bsW). The UGR is amongst the 201-300 first universities of the world, between 2nd-5th position of Spanish universities and number 1 in the Andalusian Region in the Shanghai Top 500 ranking. Specialties at UGR that stand out are Library & Information Science (position 32) and Food Science & Technology (position 36). Moreover, the UGR is also situated amongst the first 100 universities in Mining & Mineral Engineering between (76th-100th position), in Mathematics (between 76th-100th position) and in Hospitality & Tourism Management (between 76th-100th position). The edition of the ARWU places the UGR in 201-300th position in the world and as the 4th highest ranked University in Spain, reaffirming its position as an institution at the forefront of national and international research.

Additionally, the UGR has 8 researchers at the top of the Highly Cited Researchers (HCR) list in Computer Sciences & Engineering (position 101-150). It is also well recognized for its web presence (http://sl.ugr.es/0a6i), being positioned at 43th place in the top 200 Universities in Europe.

Internationally, we bet decidedly by our participation in the calls of the Framework Programme of the European Union. For the duration of the last two Framework Programmes, the UGR has obtained a total of 67 projects, with total funding of 18.029 million euros, and for H2020, 118 projects with total funding around 29.115 million euros.

Brief description of the Centre/Research Group:

Research Group "Concurrent Systems" (https://core.ugr.es/).

The CS group (TIC-157) in the Software Engineering Department at the University of Granada is made up of a multidisciplinary team of professors and research personnel, including physicists, computer and telecommunications engineers. We are interested in the theoretical and applied aspects of software development (methods, techniques, languages ​​and tools) in concurrent, embedded and real-time systems, especially applicable to domains such as control, telecommunications, home automation and instrumentation systems.

Manuel I. Capel, Full Professor of the CS Group since 2009, research interests mainly focus on the study of isomorphism between the formal modeling of real-time systems and that of other systems that also need of the formalization of temporal restrictions, such as AI methods for obtaining energy efficiency based on the prediction of consumption with variable time granularity. Selection of research projects in which prof. Manuel I. Capel participates and are directly related to the proposal:

-Big Data Modeling Under Time Restrictions For Sustainable Energy Management-ELECTRA (PID2020-112495RB-C21) PI: María del Carmen Pegalajar Jiménez. 1/09/2021-2023. 86.999,00 €

-A Development Environment for Heterogeneous Distributed Measurement Systems MAT2004-06872-C03-03) PI: Manuel I. Capel Tuñón. 13/12/2004-2007. 52.000 €.

-Development of Predictive Models of Energy Consumption in Public Buildings with Purposes of Improvement of Sustainability, Deep-E (B-TIC-302-UGR18). PI: María del Carmen Pegalajar Jiménez. 2019-2020.

Project description:

The main objective of this project would be to make a comparison of the performance improvement that involves parallelizing the training of an Artificial Neural Network (ANN), which is much time consuming for networks with a massive number of neurons. By implementing these on the GPU (we would be using CUDA/ Python + Apache Spark) as a platform for development versus the implementation of the same ANN on a CPU, we are gaining speed-up in the calculations and, at the same time, drastically reducing the training time of these networks.

The best sequential algorithm chosen, in our case, is the Backpropagation for the named Feed-Forward Multilayer NN or FMP, which possible methods of parallelization will be studied here.

Most methods of training multilayer neural networks are based on variations of the purpose of steepest descent, which frequently have bad convergence behavior. Furthermore, by adding nodes to hidden layers of a neural network, one would expect better learning behavior—however, usually it may be not the case with methods of steepest descent. On the contrary, numerical experiments show that the speed of convergence is frequently getting worse by adding new internal nodes.

There are many features that make Apache Spark a powerful framework for machine learning and data science:

• Structured Data retrieval : Spark SQL

• Machine Learning: MLlib

• Streaming Analytics: Spark Streaming

In the project, we will develop a fully functional algorithm to handle large amounts of various data efficiently and at high speed. We will use GPU devices with Python and Spark, where it allows the ability to perform an effective calculation of the data flow process and to evaluate applications that we will develop taking into consideration the implementation time and productivity.

Research Area:

  • Information Science and Engineering (ENG)

For a correct evaluation of your candidature, please send the documents below to Professor Manuel I. Capel (manuelcapel@ugr.es):

  • CV
  • Letter of recommendation (optional)


The responsibility for the hosting offers published on this website, including the hosting description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.