论文标题
预测任务的对抗性培训：确定性案例的理论分析和局限性
Adversarial training for predictive tasks: theoretical analysis and limitations in the deterministic case
论文作者
论文摘要
为了训练深层神经网络以模仿处理序列的结果，可以使用条件广义的对抗网络（CGAN）。其他人已经观察到，即使对于确定性序列，CGAN也可以帮助改善结果，在确定性序列中，只有一个输出与给定输入的处理相关。令人惊讶的是，与使用$ L_P $损失相比，我们基于CGAN的确定性地球物理处理序列的测试并没有产生真正的改进；我们在这里提出了第一个理论解释原因。我们的分析从非确定性案例转变为确定性案例。它使我们开发了一种对抗性方式来培训内容损失，从而为我们的数据提供了更好的结果。
To train a deep neural network to mimic the outcomes of processing sequences, a version of Conditional Generalized Adversarial Network (CGAN) can be used. It has been observed by others that CGAN can help to improve the results even for deterministic sequences, where only one output is associated with the processing of a given input. Surprisingly, our CGAN-based tests on deterministic geophysical processing sequences did not produce a real improvement compared to the use of an $L_p$ loss; we here propose a first theoretical explanation why. Our analysis goes from the non-deterministic case to the deterministic one. It led us to develop an adversarial way to train a content loss that gave better results on our data.
