寻求二值激活神经网络的可解释性与可说明性
Seeking Interpretability and Explainability in Binary Activated Neural Networks
AI总结：
本文研究二值激活神经网络在表格回归中的可解释性，通过表达能力保证和高效SHAP值计算量化特征与神经元重要性，并提出逐层逐神经元的贪心构建方法以获得紧凑模型。
摘要：
我们研究在表格数据回归任务背景下，将二值激活神经网络用作可解释且可说明的预测器；更具体地说，我们对其表达能力提供了保证，并提出一种基于高效计算SHAP值的方法，用于量化特征、隐藏神经元乃至权重的相对重要性。由于模型的简洁性对于实现可解释性至关重要，我们提出一种贪心算法来构建紧凑的二值激活网络。该方法无需事先固定网络架构：网络逐层、逐神经元地构建，从而得到对给定任务而言不会不必要复杂的预测器。
英文摘要：
We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks on tabular data; more specifically, we provide guarantees on their expressiveness, present an approach based on the efficient computation of SHAP values for quantifying the relative importance of the features, hidden neurons and even weights. As the model's simplicity is instrumental in achieving interpretability, we propose a greedy algorithm for building compact binary activated networks. This approach doesn't need to fix an architecture for the network in advance: it is built one layer at a time, one neuron at a time, leading to predictors that aren't needlessly complex for a given task.
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。
