We are interested in the design of generative networks. The training of these mathematical structures is mostly performed with the help of adversarial (min-max) optimization problems. We propose a simple methodology for constructing such problems assuring, at the same time, consistency of the corresponding solution. We give characteristic examples developed by our method, some of which can be recognized from other applications, and some are introduced here for the first time. We present a new metric, the likelihood ratio, that can be employed online to examine the convergence and stability during the training of different Generative Adversarial Networks (GANs). Finally, we compare various possibilities by applying them to well-known datasets using neural networks of different configurations and sizes.
翻译:我们感兴趣的是基因网络的设计,这些数学结构的培训大多是在对抗性(最小最大)优化问题的帮助下进行的。我们提出了一种简单的方法来构建这类问题,同时保证相应的解决方案的一致性。我们给出了我们的方法所开发的典型例子,其中一些可以从其他应用中得到承认,有些是首次在这里引入的。我们提出了一个新的衡量标准,即可能性比率,可以在网上使用,用于在培训不同的基因对称网络(GANs)的过程中审查趋同和稳定性。最后,我们通过使用不同配置和大小的神经网络,对各种可能性进行比较,将其应用到众所周知的数据集中。