Dr Dimitris Spathis

Contact information

Biography

Dimitris holds a PhD in Computer Science from the University of Cambridge, working with Prof. Cecilia Mascolo.

His work enables deep neural networks to learn richer semantics of high-dimensional real-world data (mobile sensors, time-series, audio, or other modalities), through self-supervision and transfer learning, motivated by challenges in health. His research has been published in top-tier artificial intelligence (NeurIPS, KDD), medical (Nature Digital Medicine), and domain-specific venues (ICASSP, Interspeech, Ubicomp), among others.

During his studies, he worked in high-profile R&D teams including Microsoft Research, Telefonica Research, Ocado, as well as growing startups and research labs. Further, he is a core member of the audio-AI study covid-19-sounds.org which builds predictive models for COVID-19 through smartphone respiratory recordings (covered by BBC, The Guardian, Forbes, The Times, Slate, NPR etc).

His career goals are to solve real problems and make AI more robust, humane, and useful.

website → http://www.cl.cam.ac.uk/~ds806/

Research interests

Machine Learning / Deep Learning
Dimensionality Reduction
Unsupervised / Transfer Learning
Time-series analysis
Health Data Science

About us

The Cambridge Centre for Data-Driven Discovery (C2D3) brings together researchers and expertise from across the academic departments and industry to drive research into the analysis, understanding and use of data science and AI. C2D3 is an Interdisciplinary Research Centre at the University of Cambridge.

  • Supports and connects the growing data science and AI research community 
  • Builds research capacity in data science and AI to tackle complex issues 
  • Drives new research challenges through collaborative research projects 
  • Promotes and provides opportunities for knowledge transfer 
  • Identifies and provides training courses for students, academics, industry and the third sector 
  • Serves as a gateway for external organisations 

Join us