物理学中的机器学习：中毒训练集的陷阱
Machine learning in physics: The pitfalls of poisoned training sets
摘要：
人工神经网络以其识别数据中隐藏模式的能力而闻名，是最强大的机器学习工具之一。最值得注意的是，神经网络在识别凝聚态物理中的物质状态和相变方面发挥了核心作用。迄今为止，大多数研究都集中在已知物质的不同相及其相变的系统上，因此神经网络的性能得到了很好的控制。虽然神经网络提供了一种令人兴奋的新工具来检测物质的新相，但在这里，我们证明了当训练集中毒时（即，训练数据不好或错误标记的数据），神经网络很容易做出误导性的预测。
英文摘要：
Known for their ability to identify hidden patterns in data, artificial neural networks are among the most powerful machine learning tools. Most notably, neural networks have played a central role in identifying states of matter and phase transitions across condensed matter physics. To date, most studies have focused on systems where different phases of matter and their phase transitions are known, and thus the performance of neural networks is well controlled. While neural networks present an exciting new tool to detect new phases of matter, here we demonstrate that when the training sets are poisoned (i.e., poor training data or mislabeled data) it is easy for neural networks to make misleading predictions.
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。
