Brain‑Inspired and Neuromorphic System Architectures

← Back to the NeuroCore 2026 Page

Call for Papers:  Brain‑Inspired and Neuromorphic System Architectures

Brain‑inspired and neuromorphic computing aims to transcend the limitations of conventional architectures by embracing principles observed in biological neural systems—massive parallelism, event‑driven signaling, sparse computation, adaptivity, and extreme energy efficiency. As emerging devices, memory technologies, and architectural paradigms mature, the field is rapidly evolving toward scalable, real‑time, and cognitively capable systems that operate far beyond the traditional von Neumann model.
This track focuses on innovations across the full architectural stack, from device‑level substrates and memory hierarchies to chip‑scale and system‑level designs that embody neural principles. We invite contributions that advance the theory, design, implementation, and evaluation of neuromorphic architectures, as well as cross‑layer approaches that tightly couple algorithms, circuits, and hardware platforms. Submissions that demonstrate practical systems, prototypes, or application‑driven neuromorphic deployments are especially encouraged.

Topics of Interest include, but are not limited to:

Brain‑Inspired and Neuromorphic Architectures

• Event‑driven, asynchronous, and massively parallel architectures
• Spiking neural network (SNN) hardware platforms
• Cognitive, adaptive, and biologically inspired system models

Architectural Design and Hardware Platforms

• Neuromorphic processors, accelerators, and heterogeneous SoCs
• Chiplet‑based, 3D‑stacked, and wafer‑scale neuromorphic systems
• Memory hierarchies and communication fabrics for neural workloads

Emerging Devices and Novel Substrates

• RRAM, PCM, FeFETs, spintronics, photonics, and other emerging devices
• Device‑architecture co‑design for neuromorphic computation
• Analog and mixed‑signal neuromorphic circuits

In‑Memory and Near‑Memory Computing

• Compute‑in‑memory (CIM) architectures for SNNs and sparse workloads
• Memory‑centric neuromorphic system design
• Algorithm–memory co‑optimization

Hardware–Software Co‑Design

• Mapping neural models to neuromorphic substrates
• Compilers, programming models, and toolchains for neuromorphic systems
• Cross‑layer optimization for latency, energy, and robustness

System‑Level Integration and Demonstrations

• End‑to‑end neuromorphic systems and prototypes
• Benchmarking, evaluation methodologies, and workload characterization
• Applications in robotics, sensing, autonomous systems, and cognitive agents

---