arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.00464stat.MLcs.LG
收藏

深度转换模型:使用基于神经网络的转换模型解决复杂回归问题

Deep transformation models: Tackling complex regression problems with neural network based transformation models

University of Zurich(苏黎世大学);Zurich University of Applied Sciences(苏黎世应用科学大学);Konstanz University of Applied Sciences(康斯坦茨应用科学大学)

Beate Sick, Torsten Hothorn, Oliver Dürr

摘要:

我们提出了一个概率回归的深度转换模型。深度学习以在复杂数据上进行非常准确的预测而闻名,但在回归任务中,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。特别是如果关键决策是基于预测的,比如在医疗应用中,量化预测的不确定性是至关重要的。所提出的深度学习转换模型估计整个条件概率分布,这是捕获结果不确定性的最彻底方法。我们将来自统计转换模型(最可能的转换)的想法与来自深度学习(标准化流)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,可以使用梯度下降与通常的极大似然框架进行训练。该方法可以与现有的深度学习架构相结合。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,部分甚至优于它。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架构来证明这一点。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑