A Synchronization-Driven Learning Rule for Pattern Separation in Self-Organizing Probabilistic Spiking Neural Networks

Abstract

Neuroscience-inspired neural networks provide a promising framework for bridging biological principles and adaptive artificial intelligence systems. Here, we propose a novel synchronization-based synaptic learning rule for self-organizing probabilistic spiking neural networks (PSNNs) with feedback inhibition. In the proposed model, synaptic plasticity is regulated by the temporal synchronization of presynaptic spike activity of single neurons, enabling unsupervised adaptation of synaptic weights and network connectivity. We systematically investigated how feedback inhibition influences network dynamics, stability, synchronization, and pattern separation efficacy. The results revealed that moderate inhibition produces an optimal balance between excitatory and inhibitory activity, maximizing pattern separation while preventing both excessive excitation and over-suppression of network activity. Comparative analysis further demonstrated that the proposed synchronization-based learning mechanism outperforms conventional Hebbian learning in achieving efficient and stable pattern separation in this neural network. Finally, the trained network was embedded in a simulated autonomous agent navigating a two-dimensional environment, where it successfully identified and avoided a learned obstacle pattern. These findings highlight the critical role of inhibitory regulation and synchronization-driven plasticity in self-organizing spiking systems and support the potential application of biologically inspired learning mechanisms in computational neuroscience, neuromorphic computing, and cognitive robotics.