Name
Abstract | ||
|---|---|---|
Incorporating higher-order optimization functions, such as Levenberg–Marquardt (LM) have revealed better generalizable solutions for deep learning problems. However, these higher-order optimization functions suffer from very large processing time and training complexity especially as training datasets become large, such as in multi-view classification problems, where finding global optima is a very costly problem. To solve this issue, we develop a solution for LM-enabled classification with, to the best of knowledge first-time implementation of hinge loss, for multiview classification. Hinge loss allows the neural network to converge faster and perform better than other loss functions such as logistic or square loss rates. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1016/j.neunet.2021.07.010 | Neural Networks |
Keywords | DocType | Volume |
Neural networks,Levenberg–Marquardt,Hinge loss,Loss functions,Classification | Journal | 143 |
Issue | ISSN | Citations |
1 | 0893-6080 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Buse Melis Ozyildirim | 1 | 18 | 2.71 |
| Mariam Kiran | 2 | 121 | 17.83 |