Biologically-Inspired Multiscale Neuromorphic Architecture

Author(s)

• Christian O'Reilly, University of South CarolinaFollow
• Ramtin Zand, University of South CarolinaFollow

ORCID iD

O'Reilly: 0000-0002-3149-4934

Zand: 0000-0002-3149-4934

Document Type

Conference Proceeding

Abstract

This white paper proposes a biologically-inspired multiscale neuromorphic architecture that bridges key gaps between artificial neural networks (ANNs), spiking neural networks (SNNs), and biological neural networks (BNNs). While SNNs offer promising energy efficiency, their broader adoption remains limited by suboptimal performance and the need for novel learning paradigms. To address these challenges, the proposed framework integrates structural and functional principles observed in the brain, including hierarchical organization, sparse and modular connectivity, predictive coding, and diverse neuronal dynamics.

The architecture operates across micro-, meso-, and macro-scales, incorporating neuron-level diversity (e.g., excitatory/inhibitory and principal/support cells), canonical microcircuits (CMCs), and large-scale hierarchical organization. CMCs serve as fundamental building blocks that segregate feedforward and feedback processing streams while enabling rich temporal dynamics such as resonance, adaptation, and reverberation. These features collectively support efficient information processing, short-term memory, and context-dependent computation.

Designed for neuromorphic implementation, the framework maps naturally onto hardware platforms such as Intel Loihi 2, leveraging event-driven computation, sparse connectivity, and on-chip learning mechanisms. The approach enables scalable, energy-efficient systems capable of adaptive and continual learning. By unifying insights from neuroscience with practical hardware considerations, this work outlines a path toward next-generation AI systems that are both biologically grounded and computationally effective.

Publication Info

Energy Consequences of Information Workshop 2026, 2026.

© 2026, Christian O'Reilly, and Ramtin Zand

APA Citation

O’Reilly, C., & Zand, R. (2026, February 2). Biologically-Inspired Multiscale Neuromorphic Architecture. Biologically-Inspired Multiscale Neuromorphic Architecture. Energy Consequences of Information Workshop 2026, Santa Fe, New Mexico USA.