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.
Faramarz Faghihi, Ahmed Moustafa, Samuel A Neymotin· Research Square· 0 citations
Background / Introduction: Biologically inspired spiking neural networks can model adaptive behavior, but learning multiple goals is difficult because synaptic updates for different targets can interfere. We tested whether multi-timescale plasticity and context-specific credit assignment could improve continual multi-goal learning in a spiking navigation system inspired by entorhinal-hippocampal circuitry. Methods: We developed a closed-loop spiking model containing grid-like, place-like, target-related, association, and motor-output populations. An agent navigated in a two-dimensional environment with randomized starting locations and learned through reward-modulated spike-timing dependent plasticity (STDP/RL) and a novel evidence-gated plasticity (EGP) framework. EGP accumulates candidate synaptic modifications, evaluates them using reward evidence, and consolidates only changes that improve performance. A target-context variant maintained separate proposal stores and reward evaluation for each target. Results: STDP/RL learned and retained a single-target navigation policy, but multi-target training produced substantial interference, including attraction to incorrect targets after learning. Across 10 connectivity seeds, target-context EGP achieved higher late-stage reward than global EGP, improved weakest-target performance, and increased the fraction of targets achieving positive reward. In a longer continual-learning simulation, reward increased for all targets, TEST-phase performance increasingly exceeded TRAIN-phase performance, and proposal magnitudes grew over learning. Dwell-time confusion analyses showed that target-context EGP reduced wrong-target attraction and improved target selectivity relative to multi-target STDP/RL. Conclusions: These results demonstrate that spiking navigation circuits can learn goal-directed behavior using local plasticity, but robust multi-goal learning benefits from context-specific evidence-based consolidation. Target-context EGP provides a biologically motivated mechanism for reducing interference during continual reinforcement learning in spiking neural networks.
Samuel A Neymotin, Hananel Hazan, Gozde Unal et al.· Research Square· 0 citations
