Galaxy Morphology Classification using Neural Ordinary Differential Equations

Galaxy Morphology Classification using Neural Ordinary Differential Equations

We use a continuous depth version of the Residual Network (ResNet) model known as Neural ordinary differential equations (NODE) for the purpose of galaxy morphology classification. We applied this method to carry out supervised classification of galaxy images from the Galaxy Zoo 2 dataset, into five distinct classes, and obtained an accuracy of about 92% for most of the classes.Through our experiments, we show that NODE not only performs as well as other deep neural networks, but has additional advantages over them, which can prove very useful for next generation surveys. We also compare our result against ResNet. While ResNet and its variants suffer problems, such as time consuming architecture selection (e.g. the number of layers) and the requirement of large data for training, NODE does not have these requirements. Through various metrics, we conclude that the performance of NODE matches that of other models, despite using only one-third of the total number of parameters as compared to these other models.

使用神经常微分方程的银河形态分类

为了星系形态分类的目的，我们使用称为神经常微分方程（NODE）的残差网络（ResNet）模型的连续深度版本。我们应用此方法对来自Galaxy Zoo 2数据集的星系图像进行了有监督的分类，分为五个不同的类别，并且大多数类别的准确度约为92％。.. 通过我们的实验，我们证明了NODE不仅具有与其他深度神经网络一样好的性能，而且在其上具有其他优势，这对于下一代调查非常有用。我们还将结果与ResNet进行比较。尽管ResNet及其变体遇到问题，例如费时的体系结构选择（例如，层数）以及需要大量数据进行培训，但NODE却没有这些要求。通过各种指标，我们得出结论，尽管与这些其他模型相比，仅使用参数总数的三分之一，但NODE的性能与其他模型相匹配。 （阅读更多）