Title: Machine/Deep Learning Techniques for Distributed Systems and Networks Intelligence

Faculty: Öznur Özkasap (oozkasap@ku.edu.tr), Barış Akgün (baakgun@ku.edu.tr)


Utilization of machine learning and deep learning techniques for enabling intelligent decisions and hence improving distributed system services is a very promising and active research area. Machine/deep learning techniques play a vital role in discovering knowledge from increasing amounts of network and system information. Hence, distributed edge intelligence is becoming increasingly significant since processing large amounts of data in a centralized manner is not always efficient due to reasons such as bandwidth/delay constraints, security, energy consumption, and fault tolerance.

We conduct research on distributed systems and reliable networks, and utilize machine/deep learning techniques for enabling novel intelligent services in distributed system technologies such as edge computing, software-defined networks, peer-to-peer (P2P) algorithms, blockchain, the Internet of Things (IoT) and information-centric networks. The applications include systems such as smart grid, P2P energy trading, vehicular networks, intelligent transportation, and smart healthcare.

We are looking for postdoctoral researchers in the fields of Distributed Systems Intelligence. The successful candidate should have a Ph.D. in Computer Science and a strong background in distributed systems, reliable networks, and machine/deep learning. The selected postdoctoral researcher will take part in the research activities at the intersection of distributed systems and artificial intelligence. S/he will demonstrate a strong commitment to research excellence, conduct innovative research in collaboration with international project partners, and participate in the supervision of graduate students. Sample project topics of interest are:

  • Blockchain-assisted Intelligent P2P Services
  • Machine/Deep Learning for Software Defined Network Intelligence
  • Deep Learning-based Edge Intelligence
  • Machine/Deep Learning for Intelligent Transportation and Vehicular Networks
  • Edge Intelligence for IoT-based Healthcare Systems
  • Decentralized Federated Machine Learning
  • Machine/Deep Learning for Industrial IoT Systems