Hajar Asgari

About

Hajar Asgari is a pioneering neuromorphic engineer whose research focuses on developing energy-efficient, event-driven spiking neural networks (SNNs) for hardware implementation. Her major contributions lie in creating digital multiplier-less architectures that enable reinforcement learning in context-dependent tasks, closely mimicking biological neural dynamics while achieving superior computational efficiency. Asgari’s most cited work (2020, 13 citations) demonstrates a breakthrough in designing SNN hardware that eliminates traditional multipliers, significantly reducing power consumption and area footprint without sacrificing learning capability. Her 2019 paper (5 citations) further refines this event-driven approach, while her 2020 follow-up (3 citations) explores the critical performance-resources trade-off inspired by the biological brain. Collectively, her research addresses the challenging problem of implementing reinforcement learning in neuromorphic systems, paving the way for ultra-low-power AI accelerators suitable for edge computing and autonomous agents. Asgari’s work stands at the intersection of neuroscience-inspired computing and practical hardware design, offering a compelling path toward brain-like efficiency in machine learning.

Research Focus

Key Achievements

Top Papers

1. 1
   Digital Multiplier-Less Spiking Neural Network Architecture of Reinforcement Learning in a Context-Dependent Task

   13 citations · 2020
2. 2
   Digital Multiplier-less Event-Driven Spiking Neural Network Architecture for Learning a Context-Dependent Task

   5 citations · 2019
3. 3
   A Digital Multiplier-less Neuromorphic Model for Learning a Context-Dependent Task

   3 citations · 2020

Key Collaborators

Contact & Links