Toward reliable machine learning models for neural circuit inference: A diagnostic study of CNNs on spike trains
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.