Michael Hopkins
Papers
1
Total Citations
24
H-Index
1
About
Michael Hopkins is a pioneering researcher at the intersection of neuromorphic computing and cognitive robotics. His work focuses on integrating spiking neural networks with physical robotic systems to achieve biologically plausible, real-time learning and behavior. Hopkins’s most cited paper, “Behavioral Learning in a Cognitive Neuromorphic Robot: An Integrative Approach” (2018, 24 citations), presents a landmark study using the iCub humanoid robot paired with the SpiNNaker neuromorphic chip to solve the challenging task of object-specific attention. This work demonstrates how spiking neural networks can drive adaptive behavior in real-world environments, despite the considerable complexity of merging neuromorphic hardware with robotic platforms. Hopkins’s research addresses a critical question: whether the added intricacy of neuromorphic integration yields tangible benefits for task performance. By showing that it does, he has helped validate the promise of brain-inspired computing for embodied AI. His contributions are shaping the future of autonomous systems that learn and interact with their surroundings more like living organisms, bridging the gap between computational neuroscience and practical robotics.
Research Focus
Key Achievements
Top Papers
- 1