用于识别分类问题的熟练预测的受控预测神经网络
Controlled abstention neural networks for identifying skillful predictions for classification problems
摘要：
地球系统在本质上是极其复杂和混乱的，这使得预测具有难以置信的挑战性：我们不能期望总是做出完美的预测。相反，我们寻找系统的特定状态，这些状态导致比其他状态更可预测的行为，通常被称为“机会预测”。当这些机会不存在时，科学家需要能够说“我不知道”的预测系统。我们引入了一种新的损失函数，称为“NotWrong损失”，它允许神经网络识别分类问题的机会预测。NotWrong损失引入了一个避免类，允许网络识别更有信心的样本，并放弃（说“我不知道”）不太有信心的样本。通过PID控制器，控制损耗被设计为放弃用户定义的样本分数。与许多用于在训练后拒绝样本的机器学习方法不同，NotWrong损失在训练期间应用，以优先从更自信的样本中学习。我们表明，在多个气候用例中，NotWrong损失优于其他现有的损失函数。在大多数为分类设计的网络架构中，所提出的损失函数的实现是直接的，因为它只需要向输出层添加一个预防类和修改损失函数。
英文摘要：
The earth system is exceedingly complex and often chaotic in nature, making prediction incredibly challenging: we cannot expect to make perfect predictions all of the time. Instead, we look for specific states of the system that lead to more predictable behavior than others, often termed "forecasts of opportunity." When these opportunities are not present, scientists need prediction systems that are capable of saying "I don't know." We introduce a novel loss function, termed the "NotWrong loss", that allows neural networks to identify forecasts of opportunity for classification problems. The NotWrong loss introduces an abstention class that allows the network to identify the more confident samples and abstain (say "I don't know") on the less confident samples. The abstention loss is designed to abstain on a user-defined fraction of the samples via a PID controller. Unlike many machine learning methods used to reject samples post-training, the NotWrong loss is applied during training to preferentially learn from the more confident samples. We show that the NotWrong loss outperforms other existing loss functions for multiple climate use cases. The implementation of the proposed loss function is straightforward in most network architectures designed for classification as it only requires the addition of an abstention class to the output layer and modification of the loss function.
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。
