Taming the Chaos in Neural Network Time Series Predictions

Machine learning methods, such as Long Short-Term Memory (LSTM) neural networks can predict real-life time series data. Here, we present a new approach to predict time series data combining interpolation techniques, randomly parameterized LSTM neural networks and measures of signal complexity, which...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sebastian Raubitzek, Thomas Neubauer
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	Hurst exponent chaos Lyapunov exponents neural networks time series prediction deep learning Science Q Astrophysics QB460-466 Physics QC1-999
Acceso en línea:	https://doaj.org/article/dc107a1fc2394f5baecd7e9e1e68e646
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dc107a1fc2394f5baecd7e9e1e68e646
record_format	dspace
spelling	oai:doaj.org-article:dc107a1fc2394f5baecd7e9e1e68e6462021-11-25T17:29:33ZTaming the Chaos in Neural Network Time Series Predictions10.3390/e231114241099-4300https://doaj.org/article/dc107a1fc2394f5baecd7e9e1e68e6462021-10-01T00:00:00Zhttps://www.mdpi.com/1099-4300/23/11/1424https://doaj.org/toc/1099-4300Machine learning methods, such as Long Short-Term Memory (LSTM) neural networks can predict real-life time series data. Here, we present a new approach to predict time series data combining interpolation techniques, randomly parameterized LSTM neural networks and measures of signal complexity, which we will refer to as complexity measures throughout this research. First, we interpolate the time series data under study. Next, we predict the time series data using an ensemble of randomly parameterized LSTM neural networks. Finally, we filter the ensemble prediction based on the original data complexity to improve the predictability, i.e., we keep only predictions with a complexity close to that of the training data. We test the proposed approach on five different univariate time series data. We use linear and fractal interpolation to increase the amount of data. We tested five different complexity measures for the ensemble filters for time series data, i.e., the Hurst exponent, Shannon’s entropy, Fisher’s information, SVD entropy, and the spectrum of Lyapunov exponents. Our results show that the interpolated predictions consistently outperformed the non-interpolated ones. The best ensemble predictions always beat a baseline prediction based on a neural network with only a single hidden LSTM, gated recurrent unit (GRU) or simple recurrent neural network (RNN) layer. The complexity filters can reduce the error of a random ensemble prediction by a factor of 10. Further, because we use randomly parameterized neural networks, no hyperparameter tuning is required. We prove this method useful for real-time time series prediction because the optimization of hyperparameters, which is usually very costly and time-intensive, can be circumvented with the presented approach.Sebastian RaubitzekThomas NeubauerMDPI AGarticleHurst exponentchaosLyapunov exponentsneural networkstime series predictiondeep learningScienceQAstrophysicsQB460-466PhysicsQC1-999ENEntropy, Vol 23, Iss 1424, p 1424 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Hurst exponent chaos Lyapunov exponents neural networks time series prediction deep learning Science Q Astrophysics QB460-466 Physics QC1-999
spellingShingle	Hurst exponent chaos Lyapunov exponents neural networks time series prediction deep learning Science Q Astrophysics QB460-466 Physics QC1-999 Sebastian Raubitzek Thomas Neubauer Taming the Chaos in Neural Network Time Series Predictions
description	Machine learning methods, such as Long Short-Term Memory (LSTM) neural networks can predict real-life time series data. Here, we present a new approach to predict time series data combining interpolation techniques, randomly parameterized LSTM neural networks and measures of signal complexity, which we will refer to as complexity measures throughout this research. First, we interpolate the time series data under study. Next, we predict the time series data using an ensemble of randomly parameterized LSTM neural networks. Finally, we filter the ensemble prediction based on the original data complexity to improve the predictability, i.e., we keep only predictions with a complexity close to that of the training data. We test the proposed approach on five different univariate time series data. We use linear and fractal interpolation to increase the amount of data. We tested five different complexity measures for the ensemble filters for time series data, i.e., the Hurst exponent, Shannon’s entropy, Fisher’s information, SVD entropy, and the spectrum of Lyapunov exponents. Our results show that the interpolated predictions consistently outperformed the non-interpolated ones. The best ensemble predictions always beat a baseline prediction based on a neural network with only a single hidden LSTM, gated recurrent unit (GRU) or simple recurrent neural network (RNN) layer. The complexity filters can reduce the error of a random ensemble prediction by a factor of 10. Further, because we use randomly parameterized neural networks, no hyperparameter tuning is required. We prove this method useful for real-time time series prediction because the optimization of hyperparameters, which is usually very costly and time-intensive, can be circumvented with the presented approach.
format	article
author	Sebastian Raubitzek Thomas Neubauer
author_facet	Sebastian Raubitzek Thomas Neubauer
author_sort	Sebastian Raubitzek
title	Taming the Chaos in Neural Network Time Series Predictions
title_short	Taming the Chaos in Neural Network Time Series Predictions
title_full	Taming the Chaos in Neural Network Time Series Predictions
title_fullStr	Taming the Chaos in Neural Network Time Series Predictions
title_full_unstemmed	Taming the Chaos in Neural Network Time Series Predictions
title_sort	taming the chaos in neural network time series predictions
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/dc107a1fc2394f5baecd7e9e1e68e646
work_keys_str_mv	AT sebastianraubitzek tamingthechaosinneuralnetworktimeseriespredictions AT thomasneubauer tamingthechaosinneuralnetworktimeseriespredictions
_version_	1718412316810149888

Taming the Chaos in Neural Network Time Series Predictions

Ejemplares similares