Scholar
Dominik Dold
Google Scholar ID: RNlSvncAAAAJ
Marie Curie Fellow, University of Vienna
Citations & Impact
Citations
576
H-index
12
i10-index
14
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published a new preprint introducing the concept of 'causal pieces' to analyze and improve spiking neural networks; published a Brennpunkt article in Physik Journal; served as an editor for Springer Astrodynamics' special issue on spAIce 2024; published Differentiable graph-structured models for inverse design of lattice materials in Cell Reports Physical Science; received funding under a Marie Curie (MSCA) Fellowship for his proposal BASE: Biologically-inspired Autonomous Systems for Space Exploration.
Research Experience
- Currently a Marie Curie Research Fellow at the Faculty of Mathematics, University of Vienna. Previously, he was a Research Fellow at the Advanced Concepts Team of the European Space Agency for three years, investigating neuro-inspired AI and methods of autonomous, functional reconfiguration for various space applications. Before that, he worked as an AI Researcher in Residence at Siemens in Munich, focusing on graph machine learning for cybersecurity and spike-based graph algorithms.
Education
- PhD in Physics from Heidelberg University and the University of Bern, focusing on neuro-inspired artificial intelligence; mainly concentrating on spiking neural networks and neuro-inspired learning rules.
Background
- Research interests include neuromorphic computing, artificial intelligence (AI), graph representation learning, and materials science. His research generally addresses the question of how complex systems composed of individual, locally interacting components can be understood and improved.
Miscellany
- Gave an invited presentation at the UCL AI Society; participated in a Dagstuhl seminar on (Actual) Neurosymbolic AI: Combining Deep Learning and Knowledge Graphs; launched the third edition of ESA's Space Optimization Competition SpOC 3.0; gave a talk at AI UK 2024 on Neuromorphic technology.
Co-authors