SHAP values accurately explain the difference in modeling accuracy of convolution neural network between soil full-spectrum and feature-spectrum.
Liang ZhongXi GuoMeng DingYingcong YeYefeng JiangQing ZhuJianlong LiPublished in: Comput. Electron. Agric. (2024)
Keyphrases
- neural network
- high accuracy
- prediction accuracy
- neural network model
- computational complexity
- feature vectors
- error rate
- computational efficiency
- back propagation
- spatial distribution
- training process
- multi layer
- neural nets
- feed forward
- radial basis function
- infrared
- artificial neural networks
- feature extraction
- decision trees
- feature selection