Felix Wege
Papers
1
Total Citations
9
H-Index
1
About
Felix Wege is a researcher at the forefront of applying evolutionary computation to computer vision, with a particular focus on robotic perception. His most cited work, "Designing Convolutional Neural Networks Using a Genetic Approach for Ball Detection" (2019), has garnered 9 citations and exemplifies his core contribution: demonstrating that genetic algorithms can autonomously design high-performing CNN architectures for real-time object detection. This innovative approach reduces the need for manual network engineering, making robust vision systems more accessible for dynamic environments like robotics. Wege’s research bridges the gap between neural architecture search and practical deployment, offering a scalable solution for tasks such as ball tracking in sports robotics. His work is notable for its integration of evolutionary principles with deep learning, paving the way for adaptive, self-optimizing vision systems. By showing that genetic methods can yield competitive detection performance, Wege has opened new avenues for automated machine learning in resource-constrained settings. For students and researchers, his contributions highlight the potential of combining bio-inspired algorithms with modern AI to solve real-world perception challenges.
Research Focus
Key Achievements
Top Papers
- 1