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 this work we systematically studied uncertainty representations in latent representations of variational auto-encoders (VAEs), both in a perceptual task from natural images and in two other canonical tasks of computer vision, finding a poor alignment between uncertainty and informativeness or ambiguities in the images. We next showed how a novel approach which we call explaining-away variational auto-encoders (EA-VAEs), fixes these issues, producing meaningful reports of uncertainty in a variety of scenarios, including interpolation, image corruption, and even out-of-distribution detection. We show EA-VAEs may prove useful both as models of perception in computational neuroscience and as inference tools in computer vision.

翻译：深度学习方法日益成为计算神经科学中的建模工具，通过最优性原则在神经响应与感知或行为之间建立桥梁。然而，深度学习在表征不确定性方面面临挑战——这类方法常存在校准问题，尤其当使用贝叶斯推断（而非仅依赖后验均值或最大后验点估计）建模皮层回路时，这一困难尤为突出。本研究系统性地探究了变分自编码器隐表示中的不确定性表征，在自然图像感知任务及两个计算机视觉经典任务中发现：不确定性信息与图像信息量或歧义性之间存在显著错位。随后我们展示了一种名为"解释性变分自编码器"（EA-VAE）的新方法，该方法可修复上述问题，在插值、图像退化乃至分布外检测等各类场景中产生有意义的不确定性报告。研究表明，EA-VAE既能作为计算神经科学中的感知模型，也可作为计算机视觉的推理工具。