Uncertainty in latent representations of variational autoencoders optimized for visual tasks

arXiv:2404.15390v1 Announce Type: new
Abstract: Deep learning methods are increasingly becoming instrumental as modeling tools in computational neuroscience, employing optimality principles to build bridges between neural responses and perception or behavior. Developing models that adequately represent uncertainty is however challenging for deep learning methods, which often suffer from calibration problems. This constitutes a difficulty in particular when modeling cortical circuits in terms of Bayesian inference, beyond single point estimates such as the posterior mean or the maximum a posteriori. In …

abstract arxiv autoencoders behavior build computational computational neuroscience cs.ai cs.lg deep learning however modeling neuroscience perception responses tasks tools type uncertainty variational autoencoders visual