Recursive Bayesian echo state network with an adaptive inflation factor for temperature prediction

Huang, Biaobing; Qin, Guihe; Zhao, Rui; Wu, Qiong; Shahriari, Alireza

doi:10.1007/s00521-016-2698-5

Cited by 13 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, in dynamic data form, the reliability of former data also needs to be considered. In [198], the authors presented a recursive Bayesian linear regression ESN (RBLR-ESN) to change the confidence level of the prior data.…”

Section: Abnormal Data Orientatedmentioning

confidence: 99%

“…Many works tested their models on this task [263]. Besides, there are also many ESN-based models designed for solar irradiance prediction [264,265,266,267,268], metereological forecasting [261,111,269], temperature prediction [198], water/stream flow forecasting [270,271,163] and wind speed Forecasting [272,131,273] • Financial applications.…”

Section: Real-world Tasks Orientatedmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Designs and Applications of Echo State Networks

Sun¹,

Song²,

Hong³

et al. 2020

Preprint

View full text Add to dashboard Cite

Recurrent Neural Networks (RNNs) have demonstrated their outstanding ability in sequence tasks and have achieved state-of-the-art in wide range of applications, such as industrial, medical, economic and linguistic. Echo State Network (ESN) is simple type of RNNs and has emerged in the last decade as an alternative to gradient descent training based RNNs. ESN, with a strong theoretical ground, is practical, conceptually simple, easy to implement. It avoids non-converging and computationally expensive in the gradient descent methods. Since ESN was put forward in 2002, abundant existing works have promoted the progress of ESN, and the recently introduced Deep ESN model opened the way to uniting the merits of deep learning and ESNs. Besides, the combinations of ESNs with other machine learning models have also overperformed baselines in some applications. However, the apparent simplicity of ESNs can sometimes be deceptive and successfully applying ESNs needs some experience. Thus, in this paper, we categorize the ESN-based methods to basic ESNs, DeepESNs and combinations, then analyze them from the perspective of theoretical studies, network designs and specific applications. Finally, we discuss the challenges and opportunities of ESNs by summarizing the open questions and proposing possible future works.

show abstract

Section: Abnormal Data Orientatedmentioning

confidence: 99%

Section: Real-world Tasks Orientatedmentioning

confidence: 99%

A Review of Designs and Applications of Echo State Networks

Sun¹,

Song²,

Hong³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Although the neural network has good self-learning ability and nonlinearity in prediction, it also has some problems such as easy to fall into local optimum, slow convergence speed, and easy to oscillate, and the number of units in the hidden layer is difficult to determine. Huang et al [14] proposed a recursive Bayesian state algorithm based on an echo state network model to predict temperature time series. As a new type of recurrent network, the echo state network overcomes the problem that traditional recurrent network is easy to fall into local optimum and its training algorithm is complex, but the random generation reservoir in the echo state network is not related to the specific issues and the parameters are difficult to determine.…”

Section: Introductionmentioning

confidence: 99%

Monthly Mean Meteorological Temperature Prediction Based on VMD-DSE and Volterra Adaptive Model

Chang

Yang

2020

Advances in Meteorology

View full text Add to dashboard Cite

Climate is a complex and chaotic system, and temperature prediction is a challenging problem. Accurate temperature prediction is also concerned in the fields of energy, environment, industry, and agriculture. In order to improve the accuracy of monthly mean temperature prediction and reduce the calculation scale of hybrid prediction process, a combined prediction model based on variational mode decomposition-differential symbolic entropy (VMD-DSE) and Volterra is proposed. Firstly, the original monthly mean meteorological temperature sequence is decomposed into finite mode components by VMD. The DSE is used to analyze the complexity and reconstruct the sequences. Then, the new sequence is reconstructed in phase space. The delay time and embedding dimension are determined by the mutual information method and G-P method, respectively. On this basis, the Volterra adaptive prediction model is established to modeling and predicting each component. Finally, the final predicted values are obtained by superimposing the predicted results. The monthly mean temperature data of Xianyang and Yan’an are used to verify the prediction performance of the proposed model. The experimental results show that the VMD-DSE-Volterra model shows better performance in the prediction of monthly mean temperature compared with other benchmark models in this paper. In addition, the combined forecasting model proposed in this paper can reduce the modeling time and improve the forecasting accuracy, so it is an effective forecasting model.

show abstract

“…The first group of optimizing approaches vary the details of original ESN, such as varying gain and bias of activation function [1], replacing normalized root mean square error (NRMSE) by correntropy [2,3] and adding Laplacian algorithm [4] to reduce the dimension of reservoir states. The second group of optimizing approaches mainly combine the ESN with other complementary neural networks or methods, including but not limited to echo state queueing networks (ESQN) [5], robust echo state networks (RESN) [2], combination structure of reservoir computing and support vector machines (RCSVM) [6], deep belief echo state network (DBESN) [7], deep recurrent neural network (DRNN) [8], optimized echo state network (OESN) by binary particle swarm optimal algorithm [9], stacked denoising autoencoders (SDA) [10], dynamical regularized echo state network (DRESN) [11], adaptive lasso echo state network (ALESN) [12], recursive Bayesian echo state network (RBESN) [13], polynomial echo state network [14], multilayered echo state network (MLESN) [15] and stacked deep echo state network (DESN) [16].…”

Section: Introductionmentioning

confidence: 99%

Deep echo state network with reservoirs of multiple activation functions for time-series prediction

Liao

2019

Sādhanā

View full text Add to dashboard Cite

In this paper, an improved deep echo state network is proposed, named as multiple activation functions deep echo state network (MAF-DESN), where states are activated by multiple activation functions. A sufficient condition for MAF-DESN is given to guarantee that MAF-DESN possesses the echo state property. Finally, the MAF-DESN is applied to chaotic time-series predictions and compared to other ESN deformation models and popular LSTM. Simulation results show that under same network size condition, MAF-DESN possesses stronger explanatory power in chaotic far-infrared laser predictions (R-square=0.9537, othersB0.6487), and better fitting ability in daily foreign exchange rates (MAE=0.0040, othersC0.0047) and chaotic far-infrared laser (MAE=3.4042, othersC4.9021). In high-dimension-input task, MAF-DESN improved the performance when the results were compared (R-square=0.4274, othersB0.3975 and MAE=5.2221, othersC7.6876), while the train time of MAF-DESN did not increase when compared to DESN.

show abstract

Recursive Bayesian echo state network with an adaptive inflation factor for temperature prediction

Cited by 13 publications

References 13 publications

A Review of Designs and Applications of Echo State Networks

A Review of Designs and Applications of Echo State Networks

Monthly Mean Meteorological Temperature Prediction Based on VMD-DSE and Volterra Adaptive Model

Deep echo state network with reservoirs of multiple activation functions for time-series prediction

Contact Info

Product

Resources

About