In which we propose neural network architecture (dune neural network) for recognizing general noisy image without adding any artificial noise in the training data. By representing each free parameter of the network as an uncertainty interval, and applying a linear transformation to each input element, we show that the resulting architecture achieves decent noise robustness when faced with input data with white noise. We apply simple dune neural networks for MNIST dataset and demonstrate that even for very noisy input images which are hard for human to recognize, our approach achieved better test set accuracy than human without dataset augmentation. We also find that our method is robust for many other examples with various background patterns added.

翻译：本文提出了一种名为“沙丘神经网络”的架构，用于识别一般性含噪图像，而无需在训练数据中添加任何人工噪声。通过将网络的每个自由参数表示为不确定区间，并对每个输入元素进行线性变换，我们证明了所提出的架构在处理带有白噪声的输入数据时能够实现显著的噪声鲁棒性。我们将简单的沙丘神经网络应用于MNIST数据集，结果表明，即使对于人类难以识别的强噪声输入图像，该方法在不进行数据集增强的情况下，仍能获得优于人类的测试集准确率。此外，我们还发现该方法对于添加了不同背景图案的多种其他样本同样具有鲁棒性。