Alexandros Bouganis

About

Alexandros Bouganis is a leading researcher in neuromorphic engineering and computational neuroscience, with a focus on bridging the gap between biological learning mechanisms and robotic control. His key research areas include spiking neural networks (SNNs), Spike Timing-Dependent Plasticity (STDP), and autonomous robotic systems. Bouganis is best known for his pioneering work on training SNNs to control complex robotic platforms, most notably demonstrated in his highly cited 2010 paper (95 citations) where he developed a spiking neural network architecture that enables a 4-degree-of-freedom robotic arm to autonomously learn joint commands through motor babbling and STDP. This work represents a significant contribution to the field of neuromorphic control, showing how biologically plausible learning rules can replace traditional control algorithms. Additionally, his research on shape recognition under occlusion (2007) introduced a fast evaluation criterion for identifying partially hidden objects, further demonstrating his versatility in computational vision. Bouganis’s work has been instrumental in advancing the application of brain-inspired computing to real-world robotics, inspiring subsequent studies in autonomous learning and adaptive control systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity

   95 citations · 2010
2. 2
   A fast evaluation criterion for the recognition of occluded shapes

   8 citations · 2007

Key Collaborators

Contact & Links