用神经网络提升可解释性，让深度学习不再黑箱。
neuralGAM: An R Package for Fitting Generalized Additive Neural Networks
- 将每个特征独立拟合神经网络，分解贡献度
- 在保持高精度的同时实现模型可解释
- 适合需要透明决策的医疗、金融等场景
如今，神经网络在异常检测、疾病辅助诊断和自然语言处理等任务中被广泛认为是最有效的方法之一。然而，这些网络存在“黑箱”问题，难以理解其决策过程。为解决此问题，本文推出名为 neuralGAM 的 R 包。该包基于广义加性模型（Generalized Additive Models）构建神经网络结构，可为每个特征独立拟合一个神经网络，以估计其对输出变量的贡献，从而得到既高精度又高度可解释的深度学习模型。neuralGAM 提供灵活的框架用于训练广义加性神经网络，不强制限制神经网络架构。文章通过合成数据与真实数据示例展示了该包的应用效果。
原文摘要 · Abstract (English)
Nowadays, Neural Networks are considered one of the most effective methods for various tasks such as anomaly detection, computer-aided disease detection, or natural language processing. However, these networks suffer from the ``black-box'' problem which makes it difficult to understand how they make decisions. In order to solve this issue, an R package called neuralGAM is introduced. This package implements a Neural Network topology based on Generalized Additive Models, allowing to fit an independent Neural Network to estimate the contribution of each feature to the output variable, yielding a highly accurate and interpretable Deep Learning model. The neuralGAM package provides a flexible framework for training Generalized Additive Neural Networks, which does not impose any restrictions on the Neural Network architecture. We illustrate the use of the neuralGAM package in both synthetic and real data examples.
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。