方法对比

	小波神经网络	多层感知机 (MLP)
领域	时间序列	深度学习
方法族	Process / pipeline	Machine learning
起源年份	1992	1986
提出者	Q. Zhang	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.
类型	Non-parametric function approximation	Supervised feedforward neural network
开创性文献	Zhang, Q., & Benveniste, A. (1992). Wavelet networks. IEEE Transactions on Neural Networks, 3(6), 889–898.	Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.
别名	WNN, Wavelet-based neural network, Wavelet networks	MLP, feedforward neural network, fully connected neural network, vanilla neural network
相关	2	4
摘要	A wavelet neural network (WNN) is a function approximation architecture that uses wavelet functions as activation functions in place of traditional sigmoid or ReLU functions. Introduced by Zhang and Benveniste (1992), WNNs combine the multiscale decomposition properties of wavelets with the learning capabilities of neural networks. The result is a flexible nonparametric model that can capture localized features and multi-resolution patterns efficiently, with fewer parameters and better interpretability than standard deep networks.	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.