论文标题
在二元激活的神经网络中寻求解释性和解释性
Seeking Interpretability and Explainability in Binary Activated Neural Networks
论文作者
论文摘要
我们研究了在表格数据上的回归任务中使用二元激活的神经网络作为可解释和可解释的预测因素的使用；更具体地说，我们提供了其表现力的保证，并基于对形状值的有效计算来介绍一种方法，以量化特征，隐藏的神经元甚至权重的相对重要性。由于该模型的简单性有助于实现可解释性，因此我们提出了一种用于构建紧凑型二元激活网络的贪婪算法。这种方法不需要事先修复网络的体系结构：一次是一个层，一次是一个神经元，从而导致预测因子对于给定的任务并不必不是复杂。
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.
