Mounir Boukadoum
Papers
8
Total Citations
142
H-Index
7
About
Mounir Boukadoum is a leading researcher in bio-inspired robotics and neural computation, whose work bridges the gap between biological learning mechanisms and autonomous robotic control. His primary research areas include spiking neural networks (SNNs), neuromorphic engineering, and human-machine interfaces for assistive technologies. Boukadoum's most significant contributions lie in demonstrating how fundamental animal learning processes—classical conditioning, operant conditioning, and habituation—can be unified under a single spike-timing-dependent plasticity (STDP) learning rule within artificial spiking neurons. His pioneering 2012 paper on classical conditioning under temporal constraints (14 citations) laid the groundwork for this unified framework, which he later expanded to encompass five variations of learning by conditioning in a single SNN architecture (2017, 7 citations). Notably, his 2014 work on operant conditioning's minimal component requirements (23 citations) provided a blueprint for building truly adaptive robot controllers. Beyond theoretical contributions, Boukadoum has achieved significant practical impact: his 2019 paper on HD-sEMG pattern recognition for robotic arm control (36 citations) and his 2015 work on intuitive wireless control for users with upper body disabilities (35 citations) demonstrate his commitment to translating neural principles into tangible assistive technologies that improve quality of life for people with disabilities.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5AI-SIMCOG: a simulator for spiking neurons and multiple animats’ behaviours14 citations · 2009
- 6
- 7
- 8