方法对比

	可解释多层感知机	多层感知机 (MLP)
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2010s–present	1986
提出者	Lundberg & Lee (SHAP); Ribeiro et al. (LIME); broader XAI community	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.
类型	Supervised feedforward neural network with interpretability layer	Supervised feedforward neural network
开创性文献	Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.	Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.
别名	XMLP, Interpretable MLP, Explainable feedforward neural network, Transparent MLP	MLP, feedforward neural network, fully connected neural network, vanilla neural network
相关	4	4
摘要	An Explainable Multilayer Perceptron (XMLP) is a standard feedforward neural network trained with backpropagation, augmented with post-hoc interpretability techniques — such as SHAP values, LIME, or integrated gradients — that attribute each prediction to individual input features. The combination retains the MLP's approximation power while satisfying transparency requirements common in regulated or high-stakes domains.	A Multilayer Perceptron is a classic fully connected feedforward neural network trained with the backpropagation algorithm, as formalised by Rumelhart, Hinton & Williams in their landmark 1986 Nature paper. Composed of an input layer, one or more hidden layers of neurons, and an output layer, the MLP learns nonlinear mappings from input features to target outputs and serves as the foundational building block of modern deep learning.