Generative Adversarial Networks (GANs) have shown remarkable success as a framework for training models to produce realistic-looking data. In this work, we propose a Recurrent GAN (RGAN) and Recurrent Conditional GAN (RCGAN) to produce realistic real-valued multi-dimensional time series, with an emphasis on their application to medical data. RGANs make use of recurrent neural networks in the generator and the discriminator. In the case of RCGANs, both of these RNNs are conditioned on auxiliary information. We demonstrate our models in a set of toy datasets, where we show visually and quantitatively (using sample likelihood and maximum mean discrepancy) that they can successfully generate realistic time-series. We also describe novel evaluation methods for GANs, where we generate a synthetic labelled training dataset, and evaluate on a real test set the performance of a model trained on the synthetic data, and vice-versa. We illustrate with these metrics that RCGANs can generate time-series data useful for supervised training, with only minor degradation in performance on real test data. This is demonstrated on digit classification from 'serialised' MNIST and by training an early warning system on a medical dataset of 17,000 patients from an intensive care unit. We further discuss and analyse the privacy concerns that may arise when using RCGANs to generate realistic synthetic medical time series data.

本文提出使用循环神经网络的生成对抗网络 (GAN) 框架来生成逼真多维时间序列数据，尤其聚焦于应用在医疗数据上。通过对玩具数据集的试验，本文证明了所提出的 RGAN 和 RCGAN 可以成功地生成逼真的时间序列数据，并在手写数字分类和医疗数据的早期预警系统等方面展示了它们在监督训练任务中的可用性。同时，本文还探讨了利用 RCGAN 生成逼真医学时间序列数据可能引起的隐私问题。

具条件循环 GAN 的实值（医学）时间序列生成