Aug 2026· PLoS Computational Biology· Vol 22, pp. e1014615· 0 citations· 51 references
Medicine
TL;DR
It is demonstrated that incorporating biologically realistic diversity during training is critical for developing reliable machine-learning tools for large-scale synaptic inference from neural recordings, and training on pooled, biologically grounded simulation data substantially improves robustness across parameter perturbations, outperforming models trained under narrow conditions.
Abstract
Understanding neuronal topology—how neurons are connected—is essential for uncovering neural computation principles and functional organization. However, accurately reconstructing such connectivity remains challenging due to the indirect nature of neural recordings and the complexity of network dynamics. As a first step towards this problem, a growing body of work has explored inferring monosynaptic connectivity directly from spike data. Among these, convolutional neural networks have shown promise when applied to spike-train cross-correlograms. Nevertheless, their ability to generalize across realistic experimental variability and the internal features that drive their predictions remain poorly understood. In this paper, we present a systematic benchmarking and diagnostic study of neural-network-based synaptic inference using simulations across a broad range of biophysical regimes. We show that connectivity classification and synaptic weight estimation, though often combined, rely on distinct internal representations and exhibit markedly different generalization behavior: robust connectivity models emphasize global structure in spike-train correlations, whereas weight estimation models are more sensitive to local signal amplitude and generalize less predictably. Importantly, we find that training on pooled, biologically grounded simulation data substantially improves robustness across parameter perturbations, outperforming models trained under narrow conditions. We further validate these findings in both simulated network data and an in vitro dataset from high‑density microelectrode array recordings with patch‑clamp‑verified ground‑truth connections. Models trained on diverse simulated circuits generalize effectively to novel network architectures and the experimental dataset. Together, these results demonstrate that incorporating biologically realistic diversity during training is critical for developing reliable machine-learning tools for large-scale synaptic inference from neural recordings.
Spike train data encapsulate precise information about neuronal firing patterns and serve as the primary modality for modeling neural dynamics. However, the variability of spike data impairs model ability to generalize across sessions and subjects. To address this gap, spike representation models are designed to extract unified neural manifolds from large-scale recordings. While recent attention-based models have demonstrated feasibility, they are constrained by deterministic architectures that are incapable of capturing the intrinsic stochasticity of neural activity and electrode-induced misalignment. To overcome these limitations, we propose the Probabilistic Neural Representation Transformer (PNRT), a framework that models variable spike activities into a consistent latent probabilistic distribution. It also implements an activity-based neuronal reordering method that decouples the model from physical electrode positions to mitigate misalignment. Validated on three cross-subject datasets, PNRT outperforms deterministic baselines in both neural consistency modeling and behavior decoding, demonstrating its capability to model unified neural representation and robustness across spike variability.
Zhijian Gong, Ning-Ling Ge, Sheng-Hao Cao et al.· IEEE transactions on neural...· 0 citations
This work presents a Hebbian local learning rule that models synaptic modification as a function of calcium traces tracking neuronal activity and demonstrates how spike timing and rate can be complementary in their role of shaping the connectivity of spiking neural networks.
Willian Soares Girāo, Nicoletta Risi, Caroline Geisler et al.· Neuromorphic Computing and E...· 0 citations
The brain can rapidly perform perception, prediction, and decision-making tasks. The capabilities stem from the collective coordination of neurons. This collective activity forms a manifold structure that naturally supports information representation and prediction, yet most neuromorphic work ignores this structure. Here, we construct an artificial neural manifold based on Mott memristors, enabling accurate and robust prediction while reducing the number of required samples. By constructing an artificial neuron circuit, a bell-shaped tuning curve similar to that of biological neurons is obtained. The tuning curve converges the large-scale neuronal firing into a compact, low-dimensional manifold structure. This structure satisfies the delay embedding theorem to establish a spatiotemporal information (STI) equation, enabling rapid prediction of neural activity with small sample sizes. In addition, we introduce a memory factor to modify the STI equation, which improves prediction accuracy and robustness. We not only accurately perceive incomplete images but also predict epileptic seizures. Inspired by collective neuronal activity, Wang et al. develop a Mott-memristor-based hardware system that maps complex spike signals to population-level artificial neural dynamics, enabling accurate prediction from limited data.
Rui Wang, Guolei Liu, Saisai Wang et al.· Nature Communications· 0 citations
Simulation results show that incorporating astrocytic modulation consistently enhances classification performance in leaky integrate-and-fire (LIF) networks, including under noisy conditions, and suggest that augmenting simplified astrocytic dynamics can improve robustness and computational capability in SNNs, while also increasing their biological plausibility.
D. Garcia, Sabir Jacquir· International Conference on...· 0 citations
Experimental results validate the effectiveness of the structure-adaptive threshold mechanism for low-power spiking graph learning and design an alternating soft-fusion-hard-grouping training strategy that decouples structure-aware threshold generation from pattern-specific threshold optimization.
Zehan Li, Yingyi Li, Juntao Zhang et al.· International Journal of Inf...· 0 citations
High-density probes record from thousands of neurons simultaneously, yet resolving single-neuron identity remains an illposed inverse problem. While detailed simulations precisely characterize the biophysical forward process, their utility for interpreting brain signal remains unclear. Here we show that biophysical simulations of population neuronal electrical signals serve as an effective bridge between theory and experiment. By pre-training artificial neural networks exclusively on large-scale synthetic data, we demonstrate robust zero-shot generalization across diverse brain regions, experimental paradigms and species, enabling the accurate inference of single-unit activities and cell-type properties without exposure to real data. Further-more, uncovering a substantial population of functionally competent but weakly active neurons systematically obscured by conventional heuristics, our framework resolves a long-standing discrepancy regarding ocular dominance in mouse primary visual cortex. These findings establish biophysical simulations as a reference standard, bridging the gap between theoretical understanding and experimental observation through data-driven inference.
