发表机构
Fraunhofer Institute for High-Speed Dynamics, Ernst-Mach-Institut, EMI（弗劳恩霍夫高速动力学研究所，恩斯特·马赫研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出高斯神经网络（GaNNs），通过在激活空间施加先验并利用无监督损失正则化，在分类与回归任务上优于标准神经网络，并能量化不确定性。
AI 中文摘要
高斯神经网络（GaNNs）被提出作为一种新颖的神经网络正则化机制。从贝叶斯视角来看，标准正则化技术可被视为在权重空间上施加先验。而在激活空间上假设先验仍是一个 largely 未被探索的可能性。GaNNs 假设了此类先验，其做法是将来自较早层的激活视为带有高斯噪声的信号，并通过一个额外的无监督损失来预测噪声分布的属性。在训练过程中，该无监督损失充当对意外激活的惩罚，从而允许在较少令人惊讶的方向上进行更大的权重更新。本文在多种分类和回归任务上证明了高斯神经网络相对于标准神经网络的优越性。我们还研究了 GaNNs 量化不确定性的能力。
英文摘要
Gaussian neural networks (GaNNs) are proposed as a novel regularization mechanism for neural networks. From a Bayesian perspective standard regularization techniques can be viewed as imposing priors over weight-space. Assuming priors over activation-space remains a largely unexplored possibility. GaNNs assume such priors. They do this by treating activities from earlier layers like signals with Gaussian noise and predicting the properties of the noise distribution using an additional unsupervised loss. While training, the unsupervised loss acts as a penalty on unexpected activities, allowing greater weight updates in less surprising directions. The paper demonstrates the superiority of Gaussian neural networks over standard neural networks on a variety of classification and regression tasks. We also investigate the ability of GaNNs to quantify uncertainty.
Comments10 pages, 5 figures. Extended abstract and poster to be presented at ICONIP 2026
