Comparer des méthodes

	Réseau à états d'écho	Réseau de neurones récurrent	Entropy d'échantillon
Domaine	Apprentissage profond	Apprentissage profond	Systèmes complexes
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2004	1986–1990	2000
Auteur d'origine	Herbert Jaeger & Harald Haas	Rumelhart, D. E.; Elman, J. L.	Richman & Moorman
Type	Recurrent neural network with fixed random reservoir	Sequential neural network	Nonlinear entropy measure
Source fondatrice	Jaeger, H., & Haas, H. (2004). Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science, 304(5667), 78–80.	Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211.	Richman, J. S., & Moorman, J. R. (2000). Physiological time-series analysis using approximate entropy and sample entropy. American Journal of Physiology, 278(6), H2039–H2049.
Alias	ESN, Liquid State Machine (related formulation), Reservoir Computing, Yankı Durum Ağı	RNN, Elman network, Jordan network, simple recurrent network	SampEn, Sample Entropy (SampEn), Örneklem Entropisi, Nonlinear Complexity Measure
Apparentées	3	3	2
Résumé	An Echo State Network (ESN) is a type of recurrent neural network introduced by Herbert Jaeger and Harald Haas in 2004 that exploits a large, randomly connected, fixed recurrent layer — the reservoir — to project input signals into a high-dimensional nonlinear space. Only the linear output weights are trained, typically via ridge regression, making ESNs computationally inexpensive yet highly expressive for temporal and chaotic time-series modeling tasks.	A Recurrent Neural Network (RNN) is a class of neural network designed to process sequential data by maintaining a hidden state that carries information across time steps. Introduced in its modern form by Rumelhart et al. (1986) and further shaped by Elman (1990), RNNs became the dominant architecture for sequence modelling in NLP, speech, and time-series analysis before the rise of attention-based models.	Sample Entropy (SampEn) is a nonlinear measure of the complexity and regularity of a time series. Introduced by Richman and Moorman in 2000 as an improvement over Approximate Entropy (ApEn), it quantifies the likelihood that similar patterns of a given length in the series remain similar when extended by one additional data point. A higher SampEn value indicates greater irregularity and complexity, while a lower value indicates more regularity or self-similarity.