Name
Abstract | ||
|---|---|---|
In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from competing classes. We propose a discriminative loss function with negative log likelihood ratio between correct and competing classes. It significantly outperforms the cross-entropy loss on the CIFAR-10 image classification task. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Learning | Neural network classification,Artificial intelligence,Generative grammar,Contextual image classification,Artificial neural network,Discriminative model,Mathematics,Negative log likelihood,Machine learning |
DocType | Volume | Citations |
Journal | abs/1804.10690 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Donglai Zhu | 1 | 0 | 0.34 |
| Heng-shuai Yao | 2 | 26 | 10.03 |
| Bei Jiang | 3 | 7 | 2.84 |
| Peng Yu | 4 | 27 | 20.15 |