变换的重要性及其在宇宙学中的应用
Transformation Importance with Applications to Cosmology
摘要：
机器学习是科学发现、知识生成和人工智能的新可能性的核心。它对这些领域的潜在好处需要超越预测的准确性，并专注于可解释性。特别是，许多科学问题需要在特定于域的可解释特征空间（例如频域）中进行解释，而对原始特征（例如像素空间）的归因可能是不可理解的甚至是误导的。为了应对这一挑战，我们提出了TRIM（transformationimportance），这是一种新的方法，它将重要性归因于变换空间中的特征，并且可以事后应用于经过充分训练的模型。TRIM的动机是在模拟数据上使用深度神经网络（DNN）的宇宙学参数估计问题，但它通常适用于跨域/模型，并且可以与任何局部解释方法相结合。在我们的宇宙学示例中，将TRIM与上下文分解相结合显示出识别DNN使用哪些频率的有希望的结果，帮助宇宙学家理解和验证模型学习适当的物理特征，而不是模拟伪影。
英文摘要：
Machine learning lies at the heart of new possibilities for scientific discovery, knowledge generation, and artificial intelligence. Its potential benefits to these fields requires going beyond predictive accuracy and focusing on interpretability. In particular, many scientific problems require interpretations in a domain-specific interpretable feature space (e.g. the frequency domain) whereas attributions to the raw features (e.g. the pixel space) may be unintelligible or even misleading. To address this challenge, we propose TRIM (TRansformation IMportance), a novel approach which attributes importances to features in a transformed space and can be applied post-hoc to a fully trained model. TRIM is motivated by a cosmological parameter estimation problem using deep neural networks (DNNs) on simulated data, but it is generally applicable across domains/models and can be combined with any local interpretation method. In our cosmology example, combining TRIM with contextual decomposition shows promising results for identifying which frequencies a DNN uses, helping cosmologists to understand and validate that the model learns appropriate physical features rather than simulation artifacts.
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。
