Ivan Baumann

About

Ivan Baumann is a leading researcher in neuromorphic computing and spiking neural networks (SNNs), with a focus on bio-inspired learning algorithms for autonomous systems. His most cited work, "Supervised Learning in SNN via Reward-Modulated Spike-Timing-Dependent Plasticity for a Target Reaching Vehicle" (2019, 41 citations), introduces a novel learning rule that combines reward-based modulation with STDP to enable efficient supervised learning in SNNs. This breakthrough addresses a key challenge in neuromorphic control—bridging the gap between biological plausibility and practical performance—by allowing SNNs to learn complex tasks like target reaching with high accuracy and low energy consumption. Baumann’s contributions have significant implications for energy-efficient robotics and edge AI, where traditional artificial neural networks (ANNs) fall short. His work has been cited by researchers advancing neuromorphic hardware and adaptive control systems, highlighting its impact on the field. Baumann continues to explore how SNNs can replicate biological learning mechanisms, positioning him as a key figure in the evolution of next-generation intelligent systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Supervised Learning in SNN via Reward-Modulated Spike-Timing-Dependent Plasticity for a Target Reaching Vehicle

   41 citations · 2019

Key Collaborators

Contact & Links