We proved that a trained model in supervised deep learning minimizes the conditional risk for each input (Theorem 2.1). This property provided insights into the behavior of trained models and established a connection between supervised and unsupervised learning in some cases. In addition, when the labels are intractable but can be written as a conditional risk minimizer, we proved an equivalent form of the original supervised learning problem with accessible labels (Theorem 2.2). We demonstrated that many existing works, such as Noise2Score, Noise2Noise and score function estimation can be explained by our theorem. Moreover, we derived a property of classification problem with noisy labels using Theorem 2.1 and validated it using MNIST dataset. Furthermore, We proposed a method to estimate uncertainty in image super-resolution based on Theorem 2.2 and validated it using ImageNet dataset. Our code is available on github.
翻译:我们证明,经过监督的深层学习模式尽量减少了每项投入的有条件风险(Theorem 2.1)。这种财产使人深入了解经过培训的模式的行为,并在某些情况下建立了受监督和不受监督的学习之间的联系;此外,如果标签难以处理,但可以作为有条件风险最小化者写成,我们用无障碍标签(Theorem 2.2)证明原始受监督的学习问题的一种同等形式(Theorem 2.2)。我们证明,许多现有的工程,如Nise2Score、Noise2Noise和得分函数估计,可以用我们的理论来解释。此外,我们利用Theorem 2.1 得出了噪音标签分类问题的性质,并利用MNIST数据集加以验证。此外,我们提出了一种方法,根据Theorem 2.2 2/ 来估计图像超分辨率的不确定性,并利用图像网络数据集加以验证。我们的代码可以在 Githhub上查阅。