论文标题
先前的选择会影响贝叶斯神经网络识别未知数的能力
Prior choice affects ability of Bayesian neural networks to identify unknowns
论文作者
论文摘要
深贝叶斯神经网络（BNN）是一种强大的工具，尽管在计算上要求进行参数估计，同时共同估计预测周围的不确定性。 BNN通常使用模型参数上的任意正常分布的先验分布来实现。在这里，我们探讨了不同先前分布对BNN中分类任务的影响，并评估基于马尔可夫链蒙特卡洛抽样和计算贝叶斯因素的后验概率的支持的证据。我们表明，先验的选择对模型有信心将数据分配给正确类别的能力（真正的正速率）有重大影响。先前的选择还会显着影响BNN识别出分布实例为未知的能力（假阳性率）。在将我们的结果与蒙特卡洛辍学的结果与神经网络（NN）进行比较时，我们发现BNN通常胜过NNS。最后，在我们的测试中，我们找不到作为先前分布的单一最佳选择。取而代之的是，每个数据集在不同的先验下产生最佳结果，表明测试替代选项可以提高BNN的性能。
Deep Bayesian neural networks (BNNs) are a powerful tool, though computationally demanding, to perform parameter estimation while jointly estimating uncertainty around predictions. BNNs are typically implemented using arbitrary normal-distributed prior distributions on the model parameters. Here, we explore the effects of different prior distributions on classification tasks in BNNs and evaluate the evidence supporting the predictions based on posterior probabilities approximated by Markov Chain Monte Carlo sampling and by computing Bayes factors. We show that the choice of priors has a substantial impact on the ability of the model to confidently assign data to the correct class (true positive rates). Prior choice also affects significantly the ability of a BNN to identify out-of-distribution instances as unknown (false positive rates). When comparing our results against neural networks (NN) with Monte Carlo dropout we found that BNNs generally outperform NNs. Finally, in our tests we did not find a single best choice as prior distribution. Instead, each dataset yielded the best results under a different prior, indicating that testing alternative options can improve the performance of BNNs.
