# Adversarial $α$-divergence Minimization for Bayesian Approximate Inference

13 Sep 2019Simón Rodríguez SantanaDaniel Hernández-Lobato

Neural networks are popular state-of-the-art models for many different tasks.They are often trained via back-propagation to find a value of the weights that correctly predicts the observed data. Although back-propagation has shown good performance in many applications, it cannot easily output an estimate of the uncertainty in the predictions made... (read more)

PDF Abstract