Examples of using 分类任务 in Chinese and their translations into English
{-}
-
Political
-
Ecclesiastic
-
Programming
这个结果在ILSVRC2015分类任务上赢得了第一名。
This result won the 1st place on the ILSVRC 2015 classification task.对于分类任务，通常使用交叉熵损失函数。
In the classification task, the cross entropy loss function is commonly used.我们现在将这个问题看作一个多类分类任务。
We treat it as multi-class classification task.首先，我们选择分类任务的整体最佳的决策树桩。
We begin by selecting 一类分类任务，输出两个互斥类别中的一个。
A type of classification task that outputs one Combinations with other parts of speech
Usage with adjectives
More
Usage with verbs
More
这些分类任务是有用的，但很直接。
These classification undertakings are useful but straightforward.此步骤通常称为分类任务。
This step is usually called the categorization task.这些组合模型往往能够在二元分类任务中取得非常不错的表现。
通过对一组8个大型文本分类任务的结果进行比较，更深层的网络比起大多较浅的网络显示出了更好的性能。
Results on a suite of 8 large text classification tasks show better performance than more shallow networks.这是机器学习中分类任务的基本思想，其中“分类”表示数据具有离散的分类标签。
This is the basic idea of a classification task in machine learning, where”classification” indicates that the data has discrete class labels.从卷积和池化层得到的大多数特征可能对分类任务有效，但这些特征的组合可能会更好。
Most of the features from convolution andpooling layers may be good for the classification task, but combinations of those features might be even better.这种处理方式在分类任务上面可以取得很好的效果，并且训练速度比sigmoid或者tanh都快很多。
It's been shown to work well in classification tasks and trains faster than sigmoid or tanh.当神经网络对图像进行训练以完成分类任务时，只有电容器的权重会被更新。
When the network is trained on images to complete a classification task, only the capacitor's weights are updated.我们的方法明显优于六个文本分类任务的最新技术，将大多数数据集的误差降低了18-24％。
Our method significantly outperforms the state-of-the-art on six text classification tasks, reducing the error by 18-24% on the majority of datasets.虽然对分类任务特别有效，但深度学习受到严重限制，并且可能以不可预知的方式失败。
While especially efficient for classification tasks, deep learning suffers from serious limits and it can fail in unpredictable ways.将定位与分类任务结合起来，就可以快速构建著名旅游景点（剪裁）图像数据集。
If it is combined with the classification task, it could allow us to quickly build a dataset of(cropped) images of famous tourist attractions.因此，对于分类任务，现在有一种计算每种类别概率的好方法了。
So, for the classification task, there is now a nice way of computing the probability of each category.采用这种方法，用户可以解决各种分类任务，而无需操作员进行繁琐的手动调整。
Users can solve various classification tasks without the tedious manual adjustment of operators.其中一些是分类任务，一些是预测任务，还有许多其他任务。
Some of these are classification tasks, some are prediction 例如，假设在CIFAR-10（一个中等规模图像分类任务）上训练两个卷积神经网络（下面的net1和net2）。
As an example, consider training two convolutional neural nets(net1 and net2, below) on CIFAR-10,a medium scale image classification task.在对Statefarm等分类任务进行微调时，我们可能需要进一步深入。
In fine-tuning for a classification task such as Statefarm, we may have to go deeper.在分类任务中，我们想要进行预测的每个个体或情况都称为观测值。
In a classification task, each individual or situation where we would like to make a prediction is called an observation.我们的方法在六种分类任务上优势明显，可以在大多数数据集上将错误率降低18-24%。
Our method significantly outperforms the state-of-the-art on six text classification tasks, reducing the error by 18-24% on the majority of datasets.最后，我们可以把这个问题看作是一个序列分类任务，其中26个字母代表一个不同的类。
Finally, we can think of this problem as a sequence classification task, where each of the 26 letters represents a different class.我们的方法在六种文本分类任务上，明显优于现有的技术，在大多数数据集上的错误减少了18~20%。
Our method significantly outperforms the state-of-the-art on six text classification tasks, reducing the error by 18-24% on the majority of datasets.随机森林是一种多功能机器学习方法，能够执行回归和分类任务。
Random forest is a machine learningmethod that is capable of performing both regression and classification tasks.许多可能的模型可以用于这样的分类任务，但是在这里我们将使用一个非常简单的模型。
There are a number of possible models for such a classification task, but here we will use an extremely simple one.熵引导变换学习：算法和应用（ETL）提出了一种用于分类任务的机器学习算法。
Entropy Guided Transformation Learning: Algorithms and Applications(ETL)presents a machine learning algorithm for classification tasks.在分类任务中，这种错误可能是假正例或者假负例。
In a classification task, this error could be a false positive or a false negative.
