论文标题
深度转换模型：通过基于神经网络的转换模型解决复杂的回归问题
Deep transformation models: Tackling complex regression problems with neural network based transformation models
论文作者
论文摘要
我们为概率回归提供了深层转化模型。深度学习以对复杂数据的出色准确预测而闻名，但是在回归任务中，它主要用于预测单个数字。这忽略了大多数任务的非确定性特征。特别是如果关键决定基于预测，例如在医学应用中，那么量化预测不确定性至关重要。提出的深度学习转化模型估计了整个条件概率分布，这是捕获结果不确定性的最彻底方法。我们将统计转换模型（最有可能转换）的思想与从深度学习（归一化流）的最新转换模型相结合，以预测复杂的结果分布。该方法的核心是一个参数化的转换函数，可以使用梯度下降使用通常的最大似然框架训练。该方法可以与现有的深度学习体系结构结合使用。对于小型机器学习基准数据集，我们报告了大多数数据集的最新性能状态，并且部分均优于它。我们的方法适用于复杂的输入数据，我们通过在图像数据上采用CNN体系结构来证明这一点。
We present a deep transformation model for probabilistic regression. Deep learning is known for outstandingly accurate predictions on complex data but in regression tasks, it is predominantly used to just predict a single number. This ignores the non-deterministic character of most tasks. Especially if crucial decisions are based on the predictions, like in medical applications, it is essential to quantify the prediction uncertainty. The presented deep learning transformation model estimates the whole conditional probability distribution, which is the most thorough way to capture uncertainty about the outcome. We combine ideas from a statistical transformation model (most likely transformation) with recent transformation models from deep learning (normalizing flows) to predict complex outcome distributions. The core of the method is a parameterized transformation function which can be trained with the usual maximum likelihood framework using gradient descent. The method can be combined with existing deep learning architectures. For small machine learning benchmark datasets, we report state of the art performance for most dataset and partly even outperform it. Our method works for complex input data, which we demonstrate by employing a CNN architecture on image data.
