Poisson Variational Autoencoder
Keywords: NeuroAI, Bayesian Inference, Predictive Coding, Sparse Coding, Variational Autoencoder
TL;DR: We introduce the PoissonVAE, a novel architecture that encodes inputs into discrete spike counts and unifies established theoretical concepts in neuroscience with modern machine learning.
Abstract: 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 significantly deviates 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-VAE encodes 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.
Primary Area: Neuroscience and cognitive science (neural coding, brain-computer interfaces)
Submission Number: 14174
Loading