用程序自动解释科学图像数据，让模型既准又可懂。
DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery
- 用大语言模型引导进化算法生成可读的Python程序
- 在人口密度估计任务上误差比非可解释模型低35%
- 适合需要理解预测逻辑的科研人员使用
视觉数据广泛应用于遥感、生态学等科学工作流。随着观测数据增多，挑战不仅在于准确预测，更在于理解预测背后的机制。良好的可解释性有助于科学决策。本文提出DiSciPLE（利用大语言模型与进化算法发现科学程序），一种自动构建可解释模型的方法，通过学习交错使用神经网络的程序来解释视觉数据。我们还引入程序评判器和简化器以优化结果。在三个真实世界问题上，DiSciPLE在无先例的新任务中学习到领先水平的程序。例如，在人口密度估计任务中，其程序误差比最近的不可解释基线降低35%。
原文摘要 · Abstract (English)
Visual data is used in numerous different scientific workflows ranging from remote sensing to ecology. As the amount of observation data increases, the challenge is not just to make accurate predictions but also to understand the underlying mechanisms for those predictions. Good interpretation is important in scientific workflows, as it allows for better decision-making by providing insights into the data. This paper introduces an automatic way of obtaining such interpretable-by-design models, by learning programs that interleave neural networks. We propose DiSciPLE (Discovering Scientific Programs using LLMs and Evolution) an evolutionary algorithm that leverages common sense and prior knowledge of large language models (LLMs) to create Python programs explaining visual data. Additionally, we propose two improvements: a program critic and a program simplifier to improve our method further to synthesize good programs. On three different real-world problems, DiSciPLE learns state-of-the-art programs on novel tasks with no prior literature. For example, we can learn programs with 35% lower error than the closest non-interpretable baseline for population density estimation.
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。