Explaining deep learning of galaxy morphology with saliency mapping
Explaining deep learning of galaxy morphology with saliency mapping
复制标题
用显着性映射解释星系形态的深度学习
DOI：
10.1093/mnras/stac368
复制
发表时间：
2022
影响因子：
4.8
通讯作者：
Bhambra P
中科院分区：
文献类型：
--
作者：
Bhambra P
我们成功地展示了使用可解释的人工智能（XAI）技术的天文数据集的背景下，测量银河酒吧的长度。该方法包括在Galaxy Zoo的人类分类数据上训练卷积神经网络，以预测一般的星系形态，然后使用SmoothGrad（一种显着映射技术）通过定制算法提取测量条。我们将其与另一种使用卷积神经网络直接预测星系棒长度的方法进行了对比。这些方法实现的相关系数为0.76和0.59，均方根误差分别为1.69和2.10人的测量。我们的结论是，在这种情况下，XAI方法优于传统的深度学习，这可以通过训练模型时可用的更大数据集来合理解释。我们建议，我们的XAI方法可以用于提取其他星系特征（例如凸起与圆盘的比例），而无需收集新的数据集或训练新的模型。我们还建议，这些技术可用于改进深度学习模型，以及识别和消除训练数据集内的偏差。
We successfully demonstrate the use of explainable artificial intelligence (XAI) techniques on astronomical data sets in the context of measuring galactic bar lengths. The method consists of training convolutional neural networks on human classified data from Galaxy Zoo in order to predict general galaxy morphologies, and then usingSmoothGrad(a saliency mapping technique) to extract the bar for measurement by a bespoke algorithm. We contrast this to another method of using a convolutional neural network to directly predict galaxy bar lengths. These methods achieved correlation coefficients of 0.76 and 0.59, and root mean squared errors of 1.69 and 2.10 respective to human measurements. We conclude that XAI methods outperform conventional deep learning in this case, which could be reasonably explained by the larger data sets available when training the models. We suggest that our XAI method can be used to extract other galactic features (such as the bulge-to-disc ratio) without needing to collect new data sets or train new models. We also suggest that these techniques can be used to refine deep learning models as well as identify and eliminate bias within training data sets.