top of page

Kosmas Deligkaris, PhD

Deep Learning and Machine Vision Engineer

  • Liknedin
  • Twitter
  • github

My current work focuses on posture tracking and 3D scene understanding for the analysis of animal behaviour. I am also interested in evolutionary algorithms and their application in optimization of neural network architectures for computer vision applications. I am a strong supporter of writing reproducible and extensible software in academia/research, as well as the utilization of agile tools for project and team management. Have a look around, and if anything comes to your mind, feel free to get in touch through the form at the bottom. 


Software development 

Developing software is perhaps the cornerstone of my work. I have worked with all kinds of different programming languages, from assembly language in microcontrollers to Fortran, and later on to Python and Java. I like developing in Java, with all its rules and patterns. For deep learning applications though, I mostly work with Python due to the extensive ecosystem and easy scripting capabilities. 

Workplace productivity ​

I have been a long user of agile tools, such as issue trackers, project managers, and knowledge repositories. In several of my previous organizations I also took the lead in establishing tools and workflows to enhance collaboration and transparency. I am mostly familiar with the Atlassian ecosystem, where I am certified as a Jira Cloud Project administrator. 

Selected Publications

Bullmann T, Radivojevic M, Huber ST, Deligkaris K, Hierlemann A and Frey U (2019)

Large-Scale Mapping of Axonal Arbors Using High-Density Microelectrode Arrays. Front. Cell. Neurosci. 13:404.

K. V. Deligkaris, Z. D. Zaharis, D. G. Kampitaki, S. K. Goudos, I. T. Rekanos and M. N. Spasos (2009)

Thinned Planar Array Design Using Boolean PSO With Velocity Mutation. IEEE Transactions on Magnetics, vol. 45, no. 3, pp. 1490-1493.

bottom of page