Comparer des méthodes

	TiDE : Encodeur Dense pour Séries Temporelles	Perceptron multicouche (MLP)	TSMixer : une architecture tout MLP pour la prévision de séries temporelles
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2023	1986	2023
Auteur d'origine	Abhimanyu Das et al.	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.	Si-An Chen et al. (Google)
Type	MLP-based encoder-decoder for long-term time-series forecasting	Supervised feedforward neural network	All-MLP multivariate time-series forecasting model
Source fondatrice	Das, A., Kong, W., Leach, A., Mathur, S., Sen, R., & Yu, R. (2023). Long-term forecasting with TiDE: Time-series dense encoder. Transactions on Machine Learning Research.	Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.	Chen, S.-A., Li, C.-L., Yoder, N., Arik, S. O., & Pfister, T. (2023). TSMixer: An all-MLP architecture for time series forecasting. Transactions on Machine Learning Research.
Alias	Time-series Dense Encoder, TiDE model, Dense Encoder for Long-term Forecasting, Yoğun Kodlayıcı Zaman Serisi Modeli	MLP, feedforward neural network, fully connected neural network, vanilla neural network	All-MLP Time Series Mixer, Time Series Mixer, TSMixer Forecasting Model, Zaman Serisi Karıştırıcı
Apparentées	3	4	3
Résumé	TiDE (Time-series Dense Encoder) is an MLP-based encoder-decoder architecture for long-term multivariate time-series forecasting, introduced by Abhimanyu Das and colleagues at Google Research in 2023. The model encodes past time-series observations together with static and dynamic covariates through stacked dense (MLP) layers, then decodes a latent representation into future forecasts. TiDE demonstrates that simple linear and dense architectures can match or outperform Transformer-based models on standard long-term forecasting benchmarks while being significantly faster.	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.	TSMixer is a multivariate time-series forecasting model introduced by Si-An Chen and colleagues at Google in 2023. It challenges the prevailing dominance of Transformer-based architectures by demonstrating that a simple stack of interleaved MLP layers — alternating between mixing along the time axis and mixing across feature channels — achieves strong forecasting accuracy while remaining computationally efficient and easy to interpret architecturally.