脉冲星分类的概率学习方法
Probabilistic learning for pulsar classification
摘要:
在这项工作中,我们探讨了使用概率学习来识别脉冲星候选者的可能性。我们使用深度高斯过程(DGP)和深度核学习(DKL)。为了避免类不平衡的影响,在平衡的训练集上训练的模型的性能,实现了区分正类和负类的相对高的概率($roc$ - $auc \sim 0.98$),总体上是非常有希望的。我们估计每个模型预测的预测熵,发现DKL在其预测中比DGP更有信心,并提供更好的不确定性校准。在研究使用不平衡数据集训练对模型的影响时,结果表明,每个模型的性能随着训练集中多数类数量的增加而下降。有趣的是,在一些负类$10\times$和正类的情况下,模型仍然提供了相当好的校准不确定性,即预期的不确定性校准误差(UCE)小于$6\%$。在这项研究中,我们还展示了在相对少量的训练数据集的情况下,通过贝叶斯不一致主动学习(BALD)训练的基于卷积神经网络的分类器的性能。我们发现,与优化数量的训练样本,该模型-是最有信心的预测-概括相对较好,并产生最佳的不确定性校准,对应于UCE = $3.118\%$。
英文摘要:
In this work, we explore the possibility of using probabilistic learning to identify pulsar candidates. We make use of Deep Gaussian Process (DGP) and Deep Kernel Learning (DKL). Trained on a balanced training set in order to avoid the effect of class imbalance, the performance of the models, achieving relatively high probability of differentiating the positive class from the negative one ($roc$-$auc \sim 0.98$), is very promising overall. We estimate the predictive entropy of each model predictions and find that DKL is more confident than DGP in its predictions and provides better uncertainty calibration. Upon investigating the effect of training with imbalanced dataset on the models, results show that each model performance decreases with an increasing number of the majority class in the training set. Interestingly, with a number of negative class $10\times$ that of positive class, the models still provide reasonably well calibrated uncertainty, i.e. an expected Uncertainty Calibration Error (UCE) less than $6\%$. We also show in this study how, in the case of relatively small amount of training dataset, a convolutional neural network based classifier trained via Bayesian Active Learning by Disagreement (BALD) performs. We find that, with an optimized number of training examples, the model -- being the most confident in its predictions -- generalizes relatively well and produces the best uncertainty calibration which corresponds to UCE = $3.118\%$.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。