Fakhoury Daniele, Fakhoury Emanuele, Speleers Hendrik
University of Rome Tor Vergata, Rome, Italy.
Neural Netw. 2022 Aug;152:332-346. doi: 10.1016/j.neunet.2022.04.029. Epub 2022 May 6.
In this paper we present ExSpliNet, an interpretable and expressive neural network model. The model combines ideas of Kolmogorov neural networks, ensembles of probabilistic trees, and multivariate B-spline representations. We give a probabilistic interpretation of the model and show its universal approximation properties. We also discuss how it can be efficiently encoded by exploiting B-spline properties. Finally, we test the effectiveness of the proposed model on synthetic approximation problems and classical machine learning benchmark datasets.
在本文中，我们提出了ExSpliNet，这是一种可解释且富有表现力的神经网络模型。该模型结合了柯尔莫哥洛夫神经网络、概率树集成和多元B样条表示的思想。我们给出了该模型的概率解释，并展示了其通用逼近特性。我们还讨论了如何通过利用B样条特性对其进行有效编码。最后，我们在合成逼近问题和经典机器学习基准数据集上测试了所提出模型的有效性。
