Georg Christian Felbinger
Papers
1
Total Citations
9
H-Index
1
About
Georg Christian Felbinger is a researcher whose work sits at the intersection of computer vision and evolutionary computation. His primary research focus is the automated design of deep learning architectures, particularly convolutional neural networks (CNNs), using genetic algorithms. His most notable contribution, the 2019 paper "Designing Convolutional Neural Networks Using a Genetic Approach for Ball Detection," demonstrates a novel method for evolving CNN topologies specifically tailored for object detection tasks. This work, which has garnered 9 citations, showcases a practical application of neuroevolution, reducing the need for manual architecture engineering in sports analytics and robotics. By combining the power of genetic search with the precision of deep learning, Felbinger addresses a key challenge in computer vision: creating efficient, task-specific models without extensive human trial-and-error. His research is particularly valuable for students and practitioners interested in automated machine learning (AutoML) and the intersection of evolutionary algorithms with real-world vision problems.
Research Focus
Key Achievements
Top Papers
- 1