Although artificial neural networks are often described as brain-inspired, their representations typically rely on continuous activations, such as the continuous latent variables in variational autoencoders (VAEs), which limits their biological plausibility compared to the discrete spike-based signaling in real neurons. Extensions like the Poisson VAE introduce discrete count-based latents, but their equal mean-variance assumption fails to capture overdispersion in neural spikes, leading to less expressive and informative representations. To address this, we propose NegBio-VAE, a negative-binomial latent-variable model with a dispersion parameter for flexible spike count modeling. NegBio-VAE preserves interpretability while improving representation quality and training feasibility via novel KL estimation and reparameterization. Experiments on four datasets demonstrate that NegBio-VAE consistently achieves superior reconstruction and generation performance compared to competing single-layer VAE baselines, and yields robust, informative latent representations for downstream tasks. Extensive ablation studies are performed to verify the model's robustness w.r.t. various components. Our code is available at https://github.com/co234/NegBio-VAE.

翻译：虽然人工神经网络常被描述为受大脑启发，但其表征通常依赖于连续激活，例如变分自编码器（VAEs）中的连续潜变量，这与真实神经元中基于离散脉冲的信号传导相比，限制了其生物学合理性。诸如泊松VAE等扩展方法引入了基于离散计数的潜变量，但其等均值-方差假设无法捕捉神经脉冲中的过离散现象，导致表征的表达能力和信息量不足。为解决这一问题，我们提出NegBio-VAE，一种带有离散参数的负二项潜变量模型，用于灵活建模脉冲计数。NegBio-VAE通过新颖的KL估计和重参数化方法，在保留可解释性的同时提升了表征质量和训练可行性。在四个数据集上的实验表明，NegBio-VAE在重构和生成性能上持续优于竞争的单层VAE基线，并为下游任务提供鲁棒且信息丰富的潜在表征。我们通过大量消融研究验证了模型各组件对鲁棒性的影响。我们的代码开源在https://github.com/co234/NegBio-VAE。