Embedded Neuromorphic Computing Systems


Khanh Dang, University of Aizu, Japan

Neuromorphic computing is inspired by the neurobiological system and opens up computing possibilities beyond traditional Von-Neumann systems. It aims to explore novel opportunities for low-power processing of sensory data for cognitive applications using spiking neural networks (SNNs).  This track aims to bring together leading researchers in neuromorphic computing systems to present new research and provide a forum to publish work in this area. The focus will be on architectures, models, and applications of embedded neuromorphic computing systems. The topics of interest of the track include, but are not limited to:

  • Neuromorphic hardware: Conventional hardware (i.e., VLSI, FPGAs) and innovative hardware (i.e., memristor) implementation of Neuromorphic systems, Compute-In-Memory Architectures, Analog/Mixed-Signal CMOS Hardware
  • Algorithms and software for neuromorphic computing systems
  • Models for neurons and synapses
  • Spiking neural-inspired architecture building blocks
  • Reliable communication networks for neuro-inspired chips/systems
  • Reconfigurability and adaptability methods
  • Deep learning models
  • New applications of on-chip learning (i.e., mobile devices, IoT, Edge).
  • Systems, architectures, and circuits: Network, neuron, and synapse models; Emerging devices and hardware implementations; Spike-based systems; Neuromorphic circuits; Novel brain-inspired system architectures
  • Software and systems for neuromorphic systems: Simulation techniques for large-scale networks; Compilers and programming frameworks; Advanced visualization tools
  • Neuromorphic Computing Applications: Robotics and Automation, High-Performance Computing, Edge Computing, Biosignal BCI

Former Chairs

  • Prof. Gianvito Urgese, Politecnico Di Torino, Italy (16th IEEE MCSoC 2023)