arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.01588cs.LGcs.AIstat.ML
收藏

nn2poly:一个用于将神经网络转换为可解释多项式的 R 包

nn2poly: An R Package for Converting Neural Networks into Interpretable Polynomials

Universidad Carlos III de Madrid(马德里卡洛斯三世大学);Universidad Pontificia Comillas(科米亚斯教皇大学)

Pablo Morala, Jenny Alexandra Cifuentes, Rosa E. Lillo, Iñaki Ucar

AI总结:

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.

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。

↑