Department of Computer Science, University of Helsinki, Finland; Helsinki Institute for Information Technology (HIIT), Helsinki, Finland.
Helsinki Institute of Physics and Department of Physics, University of Helsinki, Finland.
Neural Netw. 2021 Jan;133:123-131. doi: 10.1016/j.neunet.2020.10.002. Epub 2020 Nov 2.
Many applications, especially in physics and other sciences, call for easily interpretable and robust machine learning techniques. We propose a fully gradient-based technique for training radial basis function networks with an efficient and scalable open-source implementation. We derive novel closed-form optimization criteria for pruning the models for continuous as well as binary data which arise in a challenging real-world material physics problem. The pruned models are optimized to provide compact and interpretable versions of larger models based on informed assumptions about the data distribution. Visualizations of the pruned models provide insight into the atomic configurations that determine atom-level migration processes in solid matter; these results may inform future research on designing more suitable descriptors for use with machine learning algorithms.
许多应用程序，尤其是在物理学和其他科学领域，需要易于解释和稳健的机器学习技术。我们提出了一种完全基于梯度的技术，用于训练径向基函数网络，并提供了一个高效且可扩展的开源实现。我们为连续数据和二进制数据推导了新的闭式优化准则，这些数据出现在一个具有挑战性的现实世界材料物理问题中。修剪后的模型是基于对数据分布的明智假设，通过优化来提供更大模型的紧凑和可解释版本。修剪后的模型的可视化提供了对原子构型的深入了解，这些原子构型决定了固体物质中的原子级迁移过程；这些结果可能为未来的研究提供信息，以设计更适合机器学习算法使用的描述符。
