Variational autoencoders (VAE) employ Bayesian inference to interpret sensory
inputs, mirroring processes that occur in primate vision across both ventral
(Higgins et al., 2021) and dorsal (Vafaii et al., 2023) pathways. Despite their
success, traditional VAEs rely on continuous latent variables, which deviates
sharply from the discrete nature of biological neurons. Here, we developed the
Poisson VAE (P-VAE), a novel architecture that combines principles of
predictive coding with a VAE that encodes inputs into discrete spike counts.
Combining Poisson-distributed latent variables with predictive coding
introduces a metabolic cost term in the model loss function, suggesting a
relationship with sparse coding which we verify empirically. Additionally, we
analyze the geometry of learned representations, contrasting the P-VAE to
alternative VAE models. We find that the P-VAEencodes its inputs in relatively
higher dimensions, facilitating linear separability of categories in a
downstream classification task with a much better (5x) sample efficiency. Our
work provides an interpretable computational framework to study brain-like
sensory processing and paves the way for a deeper understanding of perception
as an inferential process.

本文介绍了一种结合了预测编码原理和将输入编码为离散脉冲计数的变分自编码器（P-VAE）的新型架构，通过引入 Poisson 分布的潜变量和预测编码，模型损失函数中出现了代谢成本项，表明与稀疏编码存在关系，我们通过实证验证了这一点。此外，我们分析了学习表示的几何结构，将 P-VAE 与其他 VAE 模型进行对比。发现 P-VAE 以相对较高的维度对输入进行编码，使下游分类任务中的类别具有线性可分性，样本效率提高了 5 倍。我们的工作提供了一个可解释的计算框架来研究类脑感觉处理，并为更深入地理解感知作为一种推理过程铺平了道路。