更多地解释深度学习模型,使用基于等级集群的模型
Elise Lunde Gjelsvik1, Kristin Tøndel1
1Faculty of Science and Technology, Norwegian University of Life Sciences, Aas, Norway.
PloS one
|December 7, 2023
概括
本研究介绍了基于层次集群的深度学习模型 (HC-CNNs,HC-RNNs,HC-SVRs) 以改进数据分析. 这些模型通过在数据集群中创建本地模型来增强可解释性,在复杂的数据集上表现优于传统方法.
科学领域:
- 机器学习 机器学习
- 化学测量 化学测量 化学测量
- 数据科学数据科学数据科学
背景情况:
- 线性模型与显示不均性或非线性数据作斗争.
- 通过数据集群进行本地建模可以提高本地线性数据的性能.
- 复杂的深度学习模型的可解释性仍然是一个挑战.
研究的目的:
- 将基于等级集群的部分最小方程回归 (HC-PLSR) 扩展到深度学习架构.
- 通过本地建模,提高深度学习模型的可解释性.
- 评估基于层次集群的新深度学习模型 (HC-CNNs,HC-RNNs,HC-SVRs) 的性能.
主要方法:
- 实施HC-CNNs,HC-RNNs和HC-SVRs.
- 在具有明显非线性关系的模拟数据集上测试模型.
- 应用到福里埃变换红外 (FT-IR) 光谱数据用于分子重量预测.
主要成果:
- 在模拟的非线性数据集上,HC-CNN,HC-RNN和HC-SVR的表现优于HC-PLSR.
- 对于FT-IR数据,复杂的模型比HC-PLSR提供了最小的预测收益.
- 在本地模型中观察到特征重要性的显著差异,有助于解释性.
结论:
- 深度学习中的局部建模通过揭示特征重要性变异来提高可解释性.
- 层次聚类与深度学习相结合,为分析复杂数据集提供了强大的方法.
- 选择模型复杂性时,应考虑数据集的特定特征.
相关概念视频
01:29Aggregates Classification
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
01:30Typical Model Studies
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.