nn2poly 是一个 R 包,通过 NN2Poly 方法将前馈神经网络转换为等效预测的可解释多项式,提取变量及其交互作用的影响,并支持 tensorflow 和 torch 等深度学习框架。
摘要:
nn2poly 包提供了 NN2Poly 方法的 R 语言实现,通过以与原始网络等效的方式进行预测的多项式表示,来解释和诠释前馈神经网络。通过获得的多项式系数,可以表示每个变量及其相互作用对输出的影响和重要性。这种捕获相互作用的能力是大多数可解释人工智能(XAI)方法通常缺失的一个关键方面,特别是当它们依赖于昂贵的计算时,这种计算在应用于大型神经网络时可能会被放大。该包提供了与 R 中主要深度学习框架包(tensorflow 和 torch)的集成,允许用户友好地应用 NN2Poly 算法。此外,nn2poly 提供了在这些相同框架中网络训练期间使用的所需权重约束的实现。其他神经网络包也可以通过将其权重包含为列表格式来使用。使用 nn2poly 获得的多项式也可用于使用新数据进行预测,或通过其自身的绘图方法进行可视化。提供了模拟示例,展示了该包的用法,并与 R 中可用的其他解释神经网络的方法进行了比较。
英文摘要:
The nn2poly package provides the implementation in R of the NN2Poly method to explain and interpret feed-forward neural networks by means of polynomial representations that predict in an equivalent manner as the original network.Through the obtained polynomial coefficients, the effect and importance of each variable and their interactions on the output can be represented. This capabiltiy of capturing interactions is a key aspect usually missing from most Explainable Artificial Intelligence (XAI) methods, specially if they rely on expensive computations that can be amplified when used on large neural networks. The package provides integration with the main deep learning framework packages in R (tensorflow and torch), allowing an user-friendly application of the NN2Poly algorithm. Furthermore, nn2poly provides implementation of the required weight constraints to be used during the network training in those same frameworks. Other neural networks packages can also be used by including their weights in list format. Polynomials obtained with nn2poly can also be used to predict with new data or be visualized through its own plot method. Simulations are provided exemplifying the usage of the package alongside with a comparison with other approaches available in R to interpret neural networks.
neuralGAM: An R Package for Fitting Generalized Additive Neural Networks
Galician Research and Development Center in Advanced Telecommunications (Gradiant)(加利西亚先进电信研究与发展中心(Gradiant));Galician Centre for Mathematical Research and Technology (CITMAga)(加利西亚数学研究与技术中心(CITMAga));Universidade de Vigo, Department of Statistics and O.R. & SiDOR Group(维戈大学统计与运筹学系及SiDOR小组)
ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs
University of Georgia(佐治亚大学);University of Texas at Arlington(德克萨斯大学阿灵顿分校);New York University Shanghai(上海纽约大学);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院)
An Interpretable Deep Learning Framework for Discovery and Clinical Validation of Deep Radiomic Signatures in Tumor Classification
Department of Health Outcomes and Biomedical Informatics, University of Florida(健康结果与生物医学信息学系,佛罗里达大学);Tiktok;Department of Biostatistics, MD Anderson Cancer Center(生物统计学系,MD安德森癌症中心);Department of Urology, University of Florida(泌尿科,佛罗里达大学)
Adaptive wavelet distillation from neural networks through interpretations
UC Berkeley(加州大学伯克利分校);CEA(法国原子能委员会);CNRS(法国国家科学研究中心);Université Paris-Saclay(巴黎-萨克雷大学);Université Paris Diderot(巴黎狄德罗大学);Sorbonne Paris Cité(索邦巴黎西岱大学)
LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs
Massachusetts Institute of Technology(麻省理工学院);Broad Institute of MIT and Harvard(麻省理工学院和哈佛大学布罗德研究所);University of Tübingen(图宾根大学);Microsoft Research(微软研究院);NYU Langone Health(纽约大学朗格尼医学中心)
A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data
Department of Physics, Boston University(波士顿大学物理系);Institute for Clinical Research and Health Policy Studies, Tufts Medical Center(塔夫茨医疗中心临床研究与健康政策研究所);Department of Medicine, School of Medicine, Tufts University(塔夫茨大学医学院医学系);Data Intensive Study Center, Tufts University(塔夫茨大学数据密集型研究中心);Division of Computational Biomedicine, Boston University Chobanian & Avedisian School of Medicine(波士顿大学Chobanian与Avedisian医学院计算生物医学系);Department of Biostatistics, Boston University School of Public Health(波士顿大学公共卫生学院生物统计学系);Bioinformatics Program, Faculty of Computing and Data Science, Boston University(波士顿大学计算与数据科学学院生物信息学项目)
deepregression: a Flexible Neural Network Framework for Semi-Structured Deep Distributional Regression
LMU Munich(慕尼黑大学);Helmholtz AI(亥姆霍兹人工智能研究所);ETH Zurich(苏黎世联邦理工学院);University of Zurich(苏黎世大学);Humboldt-Universität zu Berlin(柏林洪堡大学);Helmholtz Zentrum Munich(慕尼黑亥姆霍兹中心);Flatiron Institute(弗莱提荣研究所)