机器学习模型虽弱受领域理论影响，但跨学科迁移仍受限于理论偏见。
Machine Learning and Theory Ladenness -- A Phenomenological Account
- 通过类比现象学模型，揭示机器学习建模对领域知识不敏感
- 模型仅在弱意义上受理论污染，但影响跨领域适用性
- 推动学界从描述性讨论转向规范性反思
本文分析了科学中机器学习的理论负载问题，其中“理论”指所用领域的学科知识（称作‘领域理论’）。通过将机器学习模型与现象学模型对比，我们发现机器学习建模过程总体上对领域理论不敏感，尽管模型仍以较弱形式存在理论感染。这一观点挑战了当前科学哲学中的主流趋势，认为该结论对机器学习在不同科学领域的可迁移性具有深远影响，并促使关于理论负载的讨论从描述性转向规范性。
原文摘要 · Abstract (English)
We provide an analysis of theory ladenness in machine learning in science, where "theory", that we call "domain theory", refers to the domain knowledge of the scientific discipline where ML is used. By constructing an account of ML models based on a comparison with phenomenological models, we show, against recent trends in philosophy of science, that ML model-building is mostly indifferent to domain theory, even if the model remains theory laden in a weak sense, which we call theory infection. These claims, we argue, have far-reaching consequences for the transferability of ML across scientific disciplines, and shift the priorities of the debate on theory ladenness in ML from descriptive to normative.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。