Friedrich Solowjow
Papers
3
Total Citations
11
H-Index
2
About
Friedrich Solowjow’s research lies at the intersection of machine learning, causal inference, and control theory, with a focus on data-driven approaches for complex dynamical systems. His most cited work introduces a novel method for multimodal, multi-user surface recognition using the kernel two-sample test, offering a powerful alternative to traditional deep learning by eliminating the need for extensive data labeling and parameter tuning—a contribution that has already garnered 6 citations since its 2023 publication. Solowjow has also advanced the control of heterogeneous stochastic growth processes on lattices under resource constraints, addressing directional growth rates and node-specific dynamics. Furthermore, his work on identifying causal structure in dynamical systems provides a rigorous framework for extracting mathematical models from data, crucial for designing controllers in increasingly networked environments. Though early in his career, Solowjow’s integration of statistical testing with control theory marks a promising direction for autonomous systems that must learn and adapt with minimal human intervention.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Identifying Causal Structure in Dynamical Systems2 citations · 2020