From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination

2026-05-02

AI Summary

This work addresses the challenge that artificial neural networks struggle to emulate the rhythm-synchronized cognitive mechanisms observed in the cerebral cortex by proposing S2-Net, an oscillatory spiking neural network. The model integrates bidirectional coupling between microscopic spiking neuron dynamics and macroscopic oscillatory synchrony, incorporating a time-delayed synchronization mechanism to capture local and transient neural synchrony. Rhythmic timing is leveraged as a core learning primitive to orchestrate distributed spiking activity. By combining predefined connection scaffolds, history-dependent spike accumulation within a limited memory window, and top-down synchrony modulation, S2-Net demonstrates superior performance in neural decoding, low-power signal processing, temporal binding, and semantic reasoning, offering a novel synchrony-based coding paradigm for brain-inspired computing.

Abstract

Human cognition emerges from coordinated spiking dynamics in distributed neural circuits, where information is encoded via both firing rates and precise spike timing determined by brain rhythms. Inspired by this notion, we propose a brain-inspired learning primitive in which cognition-level neural synchrony emerges through iterative bottom-up and top-down interactions between micro-scale dynamics of spiking neurons and a macro-scale mechanism of oscillatory synchronization. Specifically, we model each parcel (e.g., a cortical region or an image pixel) in the target system as a spiking neuron embedded in a predefined connectivity scaffold. Low-level information is encoded in a spatiotemporal domain, where neurons are selectively grouped and fire spontaneously over time through self-organized dynamics. In the bottom-up route, oscillatory synchronization is formed from past spiking activity accumulated over a finite memory window. Since brain dynamics operate in a regime of partial and transient synchronization rather than global phase locking, we model oscillatory coordination using a time-delayed synchronization formulation, which enables a top-down modulation of heterogeneous neural spiking for a large-scale distributed system. Together, we devise a spiking-by-synchronization neural network (S2-Net) that uses rhythmic timing as a control mechanism for efficient information processing. Promising results have been achieved across a broad range of tasks, including neural activity decoding, energy-efficient signal processing, temporal binding and semantic reasoning.

Problem

• neural synchrony
• spiking neural network
• oscillatory coordination
• brain-inspired learning
• temporal coding

Innovation

• Oscillatory Synchronization
• Spiking Neural Network
• Time-Delayed Coordination
• Neural Synchrony
• Brain-Inspired Learning