Number of necessary training examples for Neural Networks with different number of trainable parameters

• Main Authors: Th.I. Götz (Author), S. Göb (Author), S. Sawant (Author), X.F. Erick (Author), T. Wittenberg (Author), C. Schmidkonz (Author), A.M. Tomé (Author), E.W. Lang (Author), A. Ramming (Author)
• Format: Book
• Published: Elsevier, 2022-01-01T00:00:00Z.
• Subjects: article
• Online Access: Connect to this object online.

In this work, the network complexity should be reduced with a concomitant reduction in the number of necessary training examples. The focus thus was on the dependence of proper evaluation metrics on the number of adjustable parameters of the considered deep neural network. The used data set encompas...