HIGHLIGHTS
- who: M. Cristoforetti from the Italy University of have published the paper: Prominence of the training data preparation in geomagnetic storm prediction using deep neural networks, in the Journal: Scientific Reports Scientific Reports
- what: The focus of this work is the importance of how the training data are selected and used. The analysis shows that both what the authors called nominal and weighted models provide better results than the persistent benchmark and other state-of-the-art neural_network architectures.
- how: The response of the neural_networks to training procedures that differ in the preparation . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.