Poisson Variational Autoencoder.

ABSTRACT: Variational autoencoders (VAEs) employ Bayesian inference to interpret sensory inputs, mirroring processes that occur in primate vision across both ventral [1] and dorsal [2] 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

SUBMITTER: Vafaii H 

PROVIDER: S-EPMC11661288 | biostudies-literature | 2024 Dec

REPOSITORIES: biostudies-literature