Top-down inference in an early visual cortex inspired hierarchical Variational Autoencoder. (arXiv:2206.00436v1 [q-bio.NC])

Interpreting computations in the visual cortex as learning and inference in a
generative model of the environment has received wide support both in
neuroscience and cognitive science. However, hierarchical computations, a
hallmark of visual cortical processing, has remained impervious for generative
models because of a lack of adequate tools to address it. Here we capitalize on
advances in Variational Autoencoders (VAEs) to investigate the early visual
cortex with sparse coding hierarchical VAEs trained on natural images. We
design alternative architectures …

arxiv autoencoder bio cortex hierarchical inference top