HIGHLIGHTS
- who: Enrique S. Marquez and colleagues from the (UNIVERSITY) have published the Article: Deep Cascade Learning, in the Journal: (JOURNAL) of 11,/Nov/2018
- what: The authors propose a novel approach for efficient training of deep neural networks in a bottom-up fashion using a layered structure. The authors demonstrate the algorithm on networks of convolutional layers though its applicability is more general. The authors aim to directly tackle the vanishing gradient problem by proposing a training algorithm that trains the network from the bottomto-top layer incrementally, and ensures that the layers being trained . . .
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.