New
Talk at RCC26 Conference 2026
Talk on "Understanding Structure-Function Relationships through PerformanceDependent Network Evolution" delivered at RCC26.
About me...
I develop bio-inspired machine learning systems and physics-informed digital twins for engineering applications — designed to learn fast, generalize well, and run efficiently.
My work spans Liquid State Machines/Reservoir Computing (a biologically-inspired ML paradigm ideal for edge deployment and structural monitoring), optimal network design (how topology shapes learning), and nonlinear dynamics (bifurcation-aware modeling with minimal data).
At TU Berlin, I develop dynamics-informed learning systems for structural mechanics as part of DFG SPP 2353. Previously, I built a theoretical framework for biochemical information processing at the MPI, Bonn — work that now informs my approach to bio-inspired and neuromorphic ML architectures.
I’m interested in 🤝collaborations and roles at the intersection of efficient AI, nature-inspired neuromorphic computing, and physics-constrained learning.
Research interests
Nonlinear Dynamics
Complex Networks
Machine Learning
Biochemical Networks
Cellular Information Processing
Explainable AI
Reservoir Computing
Bio-Inspired Machines
📰 Latest News
- 27 Mar 2026
🎤 Delivered a talk at RCC26 conference: Understanding Structure-Function Relationships through PerformanceDependent Network Evolution. - 13 Mar 2026
🆕📄 New preprint on arXiv: Emergent E-I Structure in Performance-Evolved Reservoir Networks of Neuronal Population Dynamics. - 10 Mar 2026
🆕🚀New article published in GAMMAS: Reservoir Computing for image classification. - 10 Dec 2025
🎤 Presented “Hierarchical Reasoning Model„ By Sapient Intelligence, Singapore, 2025 in ML-Journal Club at CPS-ME, TU Berlin. - Sep 2025
🎤 Invited as Keynote Speaker at the 11th GACM Colloquium in TU Braunschweig to present on Foundations, Theory and Applications of Reservoir Computing. - Aug 2025
📄 New paper published in Chaos: Task-specific node pruning enhances computational efficiency of reservoir computing networks. - Jun 2025
📊 Poster presentation at the PKS Workshop on Large-scale Dynamical Systems at MPI Dresden on Efficient Network Generation with Performance-Dependent Evolution. - Dec 2024
📄 New paper in Nonlinear Dynamics: Predicting multi-parametric dynamics using reservoir computing and minimal data. - Oct 2024
🚀 Launched PyReCo - a Python library for Reservoir Computing now available on PyPI. - Mar 2024
🎤 Presented at the 94th GAMM Annual Meeting in Magdeburg, Germany. - Apr 2023
🔬 Joined the DFG SPP 2353 Project on Dynamics-Informed Reservoir Computing at TU Berlin.
Featured Research & Projects
Trending
Reservoir Computing Conference 2026 (RCC26), TU Berlin
The Reservoir Computing Conference 2026 (RCC26) is an international conference dedicated to the field of reservoir computing and related machine learning approaches. RCC26 …
•
1 min read
Trending
AI in Bucket of water with Physical Reservoir Computer
A Berlin University Alliance (BUA) Course for engaging students with hands on research by building a Physical ML device that run on water and helping young scientists lead research …
•
1 min read
New
Preprint
Network structure-function relationship | New Preprint
This project has been started to understand emergent structure-function relationship of evolving networks. Part-1: Performance-Dependent Network Evolution (PDNE) framework. I …
•
2 min read
PyReCo Library
PyReCo is a Python based library built by researchers for researchers: we aim to develop new RC methods that allow for fast and efficient learning for sequential data. The main …
Featured Publications
Trending
New
Preprint
Emergent E-I Structure in Performance-Evolved Reservoir Networks of Neuronal Population Dynamics
Performance-dependent network evolution is applied to Wilson-Cowan neuronal dynamics, revealing compact reservoirs that generalize well and recover interpretable …
Homeorhetic regulation of cellular phenotype
Study of homeorhetic regulation mechanisms in cellular phenotype dynamics.
Trending
Evolution beats random chance: Performance-dependent network evolution for enhanced computational capacity
Can evolution beat random chances? Our answer: Yes, we have a proof! 😃
Predicting multi-parametric dynamics of an externally forced oscillator using reservoir computing and minimal data
This study uses a data-driven approach to investigate how bifurcations can be learned from a few system response measurements.
Asymmetry in the Basin Stability of Oscillation Death States Under Variation of Environment-Oscillator Links
We explore the effect of a common external system, which may be considered as a common environment, on the oscillation death(OD) states of a group of Stuart–Landau(SL) oscillators. …
Upcoming Projects
Trending
Music generation with bucket of water based Physical Reservoir Computer
Project Planning The next phase of of the project of information processing with bucket of water based Physcial Reservoir Computers is being planned to generate music with it. …
•
1 min read