مورد إلكتروني
Time series prediction using deep echo state networks
العنوان: | Time series prediction using deep echo state networks |
---|---|
عناروين إضافية: | Bucknell University Honors Theses Collection |
المؤلفون: | Kim, Taehwan |
المصدر: | Honors Theses |
بيانات النشر: | Bucknell Digital Commons 2020-01-01T08:00:00Z |
نوع الوثيقة: | Electronic Resource |
وصف مادي: | 1 electronic text ; pdf file |
مستخلص: | Artificial neural networks have been used for time series modeling and forecasting in many domains. However, they are often limited in their handling of nonlinear and chaotic data. More recently, reservoir-based recurrent neural net systems, most notably Echo State Networks (ESN), have made substantial improvements for time series modeling. Their shallow nature lend themselves to an efficient training method, but have limitations on non-stationary, non-linear chaotic time series, particularly large, multidimensional time series. In this paper, we propose a novel approach for forecasting time series data based on an additive decomposition (AD) applied to the time series as a preprocessor to a deep echo state network. We compare the performance of our method, AD-DeepESN, on popular neural net architectures used for time series prediction. Stationary and non-stationary data sets are used to evaluate the performance of the methods. Our results are compelling, demonstrating that AD-DeepESN has superior performance, particularly on the most challenging time series that exhibit non-stationarity and chaotic behavior compared to existing methods. |
الموضوعات: | Neural networks (Computer science), Neural circuitry., Echo state networks., Time-series analysis., Neural Networks, Computer, Nerve Net, Réseaux neuronaux (Informatique), Réseaux nerveux., Série chronologique., Neural circuitry, Neural networks (Computer science), Time-series analysis |
مصطلحات الفهرس: | text |
URL: | Bucknell University Honors Theses Collection |
الإتاحة: | Open access content. Open access content |
ملاحظة: | Keywords assigned by author: time series forecasting, reservoir computing, echo state network, additive decomposition, recurrent neural network |
أرقام أخرى: | PBU oai:digitalcommons.bucknell.edu:honors_theses-1536 https://digitalcommons.bucknell.edu/honors_theses/535 https://digitalcommons.bucknell.edu/cgi/viewcontent.cgi?article=1536&context=honors_theses 1155000033 |
المصدر المساهم: | From OAIster®, provided by the OCLC Cooperative. |
رقم الأكسشن: | edsoai.on1155000033 |
قاعدة البيانات: | OAIster |
الوصف غير متاح. |