Name
Abstract | ||
|---|---|---|
In this paper, we propose a novel approach for efficient training of deep neural networks in a bottom-up fashion using a layered structure. Our algorithm, which we refer to as deep cascade learning, is motivated by the cascade correlation approach of Fahlman and Lebiere, who introduced it in the context of perceptrons. We demonstrate our algorithm on networks of convolutional layers, though its ap... |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/TNNLS.2018.2805098 | IEEE Transactions on Neural Networks and Learning Systems |
Keywords | DocType | Volume |
Training,Computer architecture,Correlation,Convolutional codes,Backpropagation,Convolution,Complexity theory | Journal | 29 |
Issue | ISSN | Citations |
11 | 2162-237X | 5 |
PageRank | References | Authors |
0.55 | 6 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Enrique S. Marquez | 1 | 5 | 0.55 |
| J. S. Hare | 2 | 31 | 3.98 |
| Mahesan Niranjan | 3 | 775 | 120.43 |