Details
Spatially Explicit Hyperparameter Optimization for Neural Networks
|
139,09 € |
|
| Verlag: | Springer |
| Format: | |
| Veröffentl.: | 18.10.2021 |
| ISBN/EAN: | 9789811653995 |
| Sprache: | englisch |
| Anzahl Seiten: | 108 |
Dieses eBook enthält ein Wasserzeichen.
Beschreibungen
<p>Neural networks as the commonly used machine learning algorithms, such as artificial neural networks (ANNs) and convolutional neural networks (CNNs), have been extensively used in the GIScience domain to explore the nonlinear and complex geographic phenomena. However, there are a few studies that investigate the parameter settings of neural networks in GIScience. Moreover, the model performance of neural networks often depends on the parameter setting for a given dataset. Meanwhile, adjusting the parameter configuration of neural networks will increase the overall running time. Therefore, an automated approach is necessary for addressing these limitations in current studies. This book proposes an automated spatially explicit hyperparameter optimization approach to identify optimal or near-optimal parameter settings for neural networks in the GIScience field. Also, the approach improves the computing performance at both model and computing levels. This book is writtenfor researchers of the GIScience field as well as social science subjects.<br></p><br><p></p>
Chapter 1: Introduction.- Chapter 2: Literature Review.- Chapter 3: Methodology.- Chapter 4: Study I. Hyperparameter optimization of neural network-driven spatial models accelerated using cyber-enabled high-performance computing.- Chapter 5: Study II. Spatially explicit hyperparameter optimization of neural networks accelerated using high-performance computing.- Chapter 6: Study III. An integration of spatially explicit hyperparameter optimization with convolutional neural networks-based spatial models.
<p>Dr. Minrui Zheng is an Associate Professor in the School of Public Administration and Policy at Renmin University of China. She earned her M.S. in mathematical finance and her Ph.D. from the University of North Carolina at Charlotte. She has published over 10 articles in peer-reviewed journals and book chapters, and is a Member of several professional organizations including the American Association of Geographers and the North American Regional Science Council. Her research and teaching interests focus on GIScience, spatial analysis and modeling, machine learning, high-performance and parallel computing, and land change modeling. Her work focuses on using advanced spatial modeling techniques and high-performance and parallel computing to analyze big data-driven spatial problems.<br></p><br><p></p>
<p>Neural networks as the commonly used machine learning algorithms, such as artificial neural networks (ANNs) and convolutional neural networks (CNNs), have been extensively used in the GIScience domain to explore the nonlinear and complex geographic phenomena. However, there are a few studies that investigate the parameter settings of neural networks in GIScience. Moreover, the model performance of neural networks often depends on the parameter setting for a given dataset. Meanwhile, adjusting the parameter configuration of neural networks will increase the overall running time. Therefore, an automated approach is necessary for addressing these limitations in current studies. This book proposes an automated spatially explicit hyperparameter optimization approach to identify optimal or near-optimal parameter settings for neural networks in the GIScience field. Also, the approach improves the computing performance at both model and computing levels. This book is writtenfor researchers of the GIScience field as well as social science subjects.<br></p>
Explores the local variation structure of hyperparameters Presents a spatially explicit hyperparameter optimization approach, which is an improvement for existing approaches Develops an automated framework of spatially explicit hyperparameter optimization for ANN-based spatial models
Diese Produkte könnten Sie auch interessieren:
Observing Systems for Atmospheric Composition
von: Guido Visconti, Pietro Di Carlo, W. Brune, M. Schoeberl, Andreas Wahner
149,79 €
