All translations
Enter a message name below to show all available translations.
Found 3 translations.
| Name | Current message text |
|---|---|
| h English (en) | * '''MNIST''' (handwritten digits): Error reduced from 1.60% to 1.25% with {{Term|dropout}} on a standard feedforward network. * '''CIFAR-10/CIFAR-100''': Significant error reductions on convolutional networks; relative improvement of approximately 15-25% on CIFAR-100. * '''SVHN''' (Street View House Numbers): Error reduced from 2.80% to 2.68%. * '''ImageNet''': {{Term|dropout}} improved the top-1 error of a large convolutional network by approximately 2 percentage points. * '''TIMIT''' (speech recognition): Consistent improvements across various architecture sizes. * '''Reuters''' (text classification): Improved performance on a bag-of-words text classification task. |
| h Spanish (es) | * '''MNIST''' (dígitos manuscritos): error reducido del 1,60 % al 1,25 % con {{Term|dropout|dropout}} en una red feedforward estándar. * '''CIFAR-10/CIFAR-100''': reducciones significativas del error en redes convolucionales; mejora relativa de aproximadamente 15-25 % en CIFAR-100. * '''SVHN''' (Street View House Numbers): error reducido del 2,80 % al 2,68 %. * '''ImageNet''': el {{Term|dropout|dropout}} mejoró el error top-1 de una red convolucional grande en aproximadamente 2 puntos porcentuales. * '''TIMIT''' (reconocimiento de voz): mejoras consistentes en diversos tamaños de arquitectura. * '''Reuters''' (clasificación de textos): rendimiento mejorado en una tarea de clasificación de textos basada en bolsa de palabras. |
| h Chinese (zh) | * '''MNIST'''（手写数字）：在标准前馈网络上使用 {{Term|dropout|dropout}} 后，错误率从 1.60% 降至 1.25%。 * '''CIFAR-10/CIFAR-100'''：在卷积网络上显著降低错误率；在 CIFAR-100 上相对提升约 15-25%。 * '''SVHN'''（Street View House Numbers）：错误率从 2.80% 降至 2.68%。 * '''ImageNet'''：{{Term|dropout|Dropout}} 使一个大型卷积网络的 top-1 错误率改善了约 2 个百分点。 * '''TIMIT'''（语音识别）：在不同架构规模下均有一致的改进。 * '''Reuters'''（文本分类）：在词袋文本分类任务上提升了性能。 |