Shahin Hashemkhani
Papers
5
Total Citations
25
H-Index
3
About
Shahin Hashemkhani is an emerging researcher at the intersection of neuromorphic computing, bio-inspired artificial intelligence, and autonomous robotics. His work centers on translating the computational principles of biological neural systems into efficient, hardware-realizable architectures that can power next-generation intelligent machines. Hashemkhani's most-cited contribution, a bio-inspired recurrent neural network leveraging phase-change memory synapses for reinforcement learning (2020, 12 citations), demonstrated how synaptic plasticity inspired by neurobiological adaptation can be embedded directly into hardware to enable experience-driven learning. Building on this foundation, his BioNN framework (2023, 5 citations) introduced nonlinear multi-timescale feedback control to faithfully replicate the bursting rhythms of biological neurons while remaining area- and power-efficient on chip. A distinctive thread throughout his research is the application of central pattern generators — specialized neural circuits governing rhythmic locomotion — to real robotic platforms including Loihi and Arduino systems, bringing spiking neural networks out of simulation and into physical deployment. His more recent work on event-based sensorimotor control (2025) extends this vision toward fully autonomous edge robotics capable of obstacle avoidance under strict resource constraints. With a growing citation record, Hashemkhani represents a promising voice in neuromorphic and embodied AI research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5