Porovnat metody

	Vícevrstvý perceptron (MLP)	TimeMixer: Rozložitelný vícestupňový mix pro předpověď časových řad
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	1986	2024
Tvůrce	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.	Shiyu Wang et al.
Typ	Supervised feedforward neural network	MLP-based multiscale time-series forecasting model
Původní zdroj	Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.	Wang, S., Wu, H., Shi, X., Hu, T., Luo, H., Ma, L., Zhang, J. Y., & Zhou, J. (2024). TimeMixer: Decomposable multiscale mixing for time series forecasting. ICLR.
Další názvy	MLP, feedforward neural network, fully connected neural network, vanilla neural network	Decomposable Multiscale Mixing, Multiscale Time-Series Mixer, TimeMixer Model, Çok Ölçekli Zaman Serisi Karıştırıcı
Příbuzné	4	3
Shrnutí	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.	TimeMixer is a decomposition-based, attention-free time-series forecasting architecture introduced by Wang et al. at ICLR 2024. The central idea is to disentangle seasonal and trend components across multiple temporal scales constructed by average pooling, then mix information across those scales using lightweight MLP blocks. By handling coarse (trend-dominant) and fine (seasonal-dominant) resolutions separately and combining their predictions, TimeMixer avoids the quadratic cost of attention while capturing both local and global temporal patterns.