9783031880902 - fractional-order activation functions for neural networks: case studies on forecasting wind turbines' generated power: 588 di bingi, kishore; bhukya, ramadevi; kasi, venkata ramana (10 risultati)
- Rilegato
Da: Grand Eagle Retail, Bensenville, IL, U.S.A.Grand Eagle Retail
Contatta il venditoreVenditore con 5 stelleCondizione: Nuovo
EUR 207,09
Spedizione gratuitaSpedito in U.S.A.Quantità: 1 disponibili
Hardcover. Condizione: new. Hardcover. This book suggests the development of single and multi-layer fractional-order neural networks that incorporate fractional-order activation functions derived using fractional-order derivatives. Activation functions are essential in neural networks as they introduce nonlinearity, enabling the… models to learn complex patterns in data. However, traditional activation functions have limitations such as non-differentiability, vanishing gradient problems, and inactive neurons at negative inputs, which can affect the performance of neural networks, especially for tasks involving intricate nonlinear dynamics. To address these issues, fractional-order derivatives from fractional calculus have been proposed. These derivatives can model complex systems with non-local or non-Markovian behavior. The aim is to improve wind power prediction accuracy using datasets from the Texas wind turbine and Jeju Island wind farm under various scenarios. The book explores the advantages of fractional-order activation functions in terms of robustness, faster convergence, and greater flexibility in hyper-parameter tuning. It includes a comparative analysis of single and multi-layer fractional-order neural networks versus conventional neural networks, assessing their performance based on metrics such as mean square error and coefficient of determination. The impact of using machine learning models to impute missing data on the performance of networks is also discussed. This book demonstrates the potential of fractional-order activation functions to enhance neural network models, particularly in predicting chaotic time series. The findings suggest that fractional-order activation functions can significantly improve accuracy and performance, emphasizing the importance of advancing activation function design in neural network analysis. Additionally, the book is a valuable teaching and learning resource for undergraduate and postgraduate students conducting research in this field. mso-fareast-language: EN-IN;">This book suggests the development of single and multi-layer fractional-order neural networks that incorporate fractional-order activation functions derived using fractional-order derivatives. Shipping may be from multiple locations in the US or from the UK, depending on stock availability.
- Rilegato
Da: Books Puddle, New York, NY, U.S.A.Books Puddle
Contatta il venditoreVenditore con 4 stelleCondizione: Nuovo
EUR 227,70
EUR 3,50 spedizioneSpedito in U.S.A.Quantità: 4 disponibili
Condizione: New.
- Rilegato
Da: AHA-BUCH GmbH, Einbeck, GermaniaAHA-BUCH GmbH
Contatta il venditoreVenditore con 5 stelleCondizione: Nuovo
EUR 177,35
EUR 62,99 spedizioneSpedito da Germania a U.S.A.Quantità: 1 disponibili
Buch. Condizione: Neu. Druck auf Anfrage Neuware - Printed after ordering - This book suggests the development of single and multi-layer fractional-order neural networks that incorporate fractional-order activation functions derived using fractional-order derivatives. Activation functions are essential in neural networks as they… introduce nonlinearity, enabling the models to learn complex patterns in data. However, traditional activation functions have limitations such as non-differentiability, vanishing gradient problems, and inactive neurons at negative inputs, which can affect the performance of neural networks, especially for tasks involving intricate nonlinear dynamics. To address these issues, fractional-order derivatives from fractional calculus have been proposed. These derivatives can model complex systems with non-local or non-Markovian behavior. The aim is to improve wind power prediction accuracy using datasets from the Texas wind turbine and Jeju Island wind farm under various scenarios. The book explores the advantages of fractional-order activation functions in terms of robustness, faster convergence, and greater flexibility in hyper-parameter tuning. It includes a comparative analysis of single and multi-layer fractional-order neural networks versus conventional neural networks, assessing their performance based on metrics such as mean square error and coefficient of determination. The impact of using machine learning models to impute missing data on the performance of networks is also discussed. This book demonstrates the potential of fractional-order activation functions to enhance neural network models, particularly in predicting chaotic time series. The findings suggest that fractional-order activation functions can significantly improve accuracy and performance, emphasizing the importance of advancing activation function design in neural network analysis. Additionally, the book is a valuable teaching and learning resource for undergraduate and postgraduate students conducting research in this field.
- Rilegato
Da: Revaluation Books, Exeter, Regno UnitoRevaluation Books
Contatta il venditoreVenditore con 5 stelleCondizione: Nuovo
EUR 252,47
EUR 14,51 spedizioneSpedito da Regno Unito a U.S.A.Quantità: 1 disponibili
Hardcover. Condizione: Brand New. 255 pages. 9.26x6.11x9.43 inches. In Stock.
- Rilegato
- Print on Demand
Da: Brook Bookstore On Demand, Napoli, NA, ItaliaBrook Bookstore On Demand
Contatta il venditoreVenditore con 5 stelleCondizione: Nuovo
EUR 134,27
EUR 5,50 spedizioneSpedito da Italia a U.S.A.Quantità: Più di 20 disponibili
Condizione: new. Questo è un articolo print on demand.
Lingua: Inglese
Editore: Springer, Berlin, Springer Nature Switzerland, Springer, 2025
- Rilegato
- Print on Demand
Da: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, GermaniaBuchWeltWeit Ludwig Meier e.K.
Contatta il venditoreVenditore con 5 stelleCondizione: Nuovo
EUR 171,19
EUR 23,00 spedizioneSpedito da Germania a U.S.A.Quantità: 2 disponibili
Buch. Condizione: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -This book suggests the development of single and multi-layer fractional-order neural networks that incorporate fractional-order activation functions derived using fractional-order derivatives. Activation functions are essential in neural…networks as they introduce nonlinearity, enabling the models to learn complex patterns in data. However, traditional activation functions have limitations such as non-differentiability, vanishing gradient problems, and inactive neurons at negative inputs, which can affect the performance of neural networks, especially for tasks involving intricate nonlinear dynamics. To address these issues, fractional-order derivatives from fractional calculus have been proposed. These derivatives can model complex systems with non-local or non-Markovian behavior. The aim is to improve wind power prediction accuracy using datasets from the Texas wind turbine and Jeju Island wind farm under various scenarios. The book explores the advantages of fractional-order activation functions in terms of robustness, faster convergence, and greater flexibility in hyper-parameter tuning. It includes a comparative analysis of single and multi-layer fractional-order neural networks versus conventional neural networks, assessing their performance based on metrics such as mean square error and coefficient of determination. The impact of using machine learning models to impute missing data on the performance of networks is also discussed. This book demonstrates the potential of fractional-order activation functions to enhance neural network models, particularly in predicting chaotic time series. The findings suggest that fractional-order activation functions can significantly improve accuracy and performance, emphasizing the importance of advancing activation function design in neural network analysis. Additionally, the book is a valuable teaching and learning resource for undergraduate and postgraduate students conducting research in this field. 238 pp. Englisch.
- Rilegato
- Print on Demand
Da: preigu, Osnabrück, Germaniapreigu
Contatta il venditoreVenditore con 5 stelleCondizione: Nuovo
EUR 150,30
EUR 70,00 spedizioneSpedito da Germania a U.S.A.Quantità: 5 disponibili
Buch. Condizione: Neu. Fractional-Order Activation Functions for Neural Networks | Case Studies on Forecasting Wind Turbines' Generated Power | Kishore Bingi (u. a.) | Buch | Studies in Systems, Decision and Control | xvii | Englisch | 2025 | Springer | EAN 9783031880902 | Verantwortliche Person für die EU: Springer Verlag GmbH,… Tiergartenstr. 17, 69121 Heidelberg, juergen[dot]hartmann[at]springer[dot]com | Anbieter: preigu Print on Demand.
- Rilegato
- Print on Demand
Da: buchversandmimpf2000, Emtmannsberg, BAYE, Germaniabuchversandmimpf2000
Contatta il venditoreVenditore con 5 stelleCondizione: Nuovo
EUR 171,19
EUR 60,00 spedizioneSpedito da Germania a U.S.A.Quantità: 1 disponibili
Buch. Condizione: Neu. This item is printed on demand - Print on Demand Titel. Neuware -This book suggests the development of single and multi-layer fractional-order neural networks that incorporate fractional-order activation functions derived using fractional-order derivatives. Activation functions are essential in neural netw…orks as they introduce nonlinearity, enabling the models to learn complex patterns in data. However, traditional activation functions have limitations such as non-differentiability, vanishing gradient problems, and inactive neurons at negative inputs, which can affect the performance of neural networks, especially for tasks involving intricate nonlinear dynamics. To address these issues, fractional-order derivatives from fractional calculus have been proposed. These derivatives can model complex systems with non-local or non-Markovian behavior. The aim is to improve wind power prediction accuracy using datasets from the Texas wind turbine and Jeju Island wind farm under various scenarios. The book explores the advantages of fractional-order activation functions in terms of robustness, faster convergence, and greater flexibility in hyper-parameter tuning. It includes a comparative analysis of single and multi-layer fractional-order neural networks versus conventional neural networks, assessing their performance based on metrics such as mean square error and coefficient of determination. The impact of using machine learning models to impute missing data on the performance of networks is also discussed. This book demonstrates the potential of fractional-order activation functions to enhance neural network models, particularly in predicting chaotic time series. The findings suggest that fractional-order activation functions can significantly improve accuracy and performance, emphasizing the importance of advancing activation function design in neural network analysis. Additionally, the book is a valuable teaching and learning resource for undergraduate and postgraduate students conducting research in this field.Springer-Verlag KG, Sachsenplatz 4-6, 1201 Wien 256 pp. Englisch.
- Rilegato
- Print on Demand
Da: Majestic Books, Hounslow, Regno UnitoMajestic Books
Contatta il venditoreVenditore con 4 stelleCondizione: Nuovo
EUR 242,16
EUR 7,55 spedizioneSpedito da Regno Unito a U.S.A.Quantità: 4 disponibili
Condizione: New. Print on Demand.
- Rilegato
- Print on Demand
Da: Biblios, frankfurt am main, HESSE, GermaniaBiblios
Contatta il venditoreVenditore con 4 stelleCondizione: Nuovo
EUR 240,84
EUR 9,95 spedizioneSpedito da Germania a U.S.A.Quantità: 4 disponibili
Condizione: New. PRINT ON DEMAND.
