A problem that lends itself to the application of machine learning is classifying matched sources in the GALEX (Galaxy Evolution Explorer) and SDSS (Sloan Digital Sky Survey) catalogs into stars and quasars based on color-color plots. The problem is daunting because stars and quasars are still inextricably mixed elsewhere in the color-color plots and no clear linear/non-linear boundary separates the two entities. Diversity and volume of samples add to the complexity of the problem. We explore the efficacy of neural network based classification techniques in discriminating between stars and quasars using GALEX and SDSS photometric data. Both sources have compact optical morphology but are very different in nature and are at very different distances. We have used those objects with associated spectroscopic information as our training-set and built neural network and ensemble classifiers that appropriately classify photometric samples without associated spectroscopic labels. Catalogs comprising of samples labeled using our classifiers can be further used in studies of photometric sources. The design of a novel Generative Adversarial Network (GAN) based classifier is proposed in the paper to tackle the classification problem. To evaluate the correctness of the classifiers, we report the accuracy and other performance metrics and find reasonably satisfactory range of 91%–100%.

适用于机器学习的一个问题是在GALEX（Galaxy Evolution Explorer）中对匹配的源进行分类）和SDSS（斯隆数字天空调查）基于彩色图表将其分类为恒星和类星体。这个问题之所以令人生畏，是因为在彩色图中，恒星和类星体仍然不可避免地混合在一起，并且没有清晰的线性/非线性边界将这两个实体分开。样本的多样性和数量增加了问题的复杂性。我们探索使用GALEX和SDSS光度数据基于神经网络的分类技术在区分恒星和类星体中的功效。两种光源都具有紧凑的光学形态，但本质上有很大不同，并且距离也相差很大。我们将那些具有相关光谱信息的对象用作训练集，并建立了神经网络和集成分类器，它们可以对没有相关光谱标签的光度样本进行适当分类。使用我们的分类器标记的样本组成的目录可进一步用于光度学来源的研究。为了解决分类问题，本文提出了一种基于生成对抗网络的新型分类器。为了评估分类器的正确性，我们报告了准确性和其他性能指标，并找到了91％–100％的合理令人满意的范围。