Andere Kunden interessierten sich auch für
![Deep Learning in der Fernerkundung]( "Deep Learning in der Fernerkundung")
Deep Learning in der Fernerkundung43,90 €![Apprentissage profond en télédétection]( "Apprentissage profond en télédétection")
Apprentissage profond en télédétection29,99 €![Apprendimento profondo nel telerilevamento]( "Apprendimento profondo nel telerilevamento")
Apprendimento profondo nel telerilevamento29,99 €![Aprendizagem profunda na deteção remota]( "Aprendizagem profunda na deteção remota")
Aprendizagem profunda na deteção remota29,99 €![Glubokoe obuchenie w distancionnom zondirowanii]( "Glubokoe obuchenie w distancionnom zondirowanii")
Glubokoe obuchenie w distancionnom zondirowanii29,99 €![Machine Learning for Earth Sciences]( "Machine Learning for Earth Sciences")
Machine Learning for Earth Sciences44,99 €![Machine Learning for Earth Sciences]( "Machine Learning for Earth Sciences")
Machine Learning for Earth Sciences59,99 €
In this book, an overview of DL is presented that adopts various perspectives such as state-of-the-arts deep learning techniques, Deep learning approaches, applications. Additionally, the potential problems on deep learning technology. This research presents convolutional neural networks (CNNs) which the most utilized DL network type. A survey of the CNN deep learning architectures that are frequently encountered in the literature, along with their strengths and limitations and describes the development of CNNs architectures together with their main features, e.g., AlexNet, VGG, ResNet, DenseNet, GoogLeNet, Inception: ResNet nd Inception V3/ V4, SegNet, U Net, Point CNN and MASK R-CNN .A detailed study on application of Convolutional Neural Network on the remote sensing to extract features is also explained. Challenges that met CNN were discussed.