CLASSIFICATION TASKS 中文是什么意思 - 中文翻译

• 分类任务

在 英语 中使用 Classification tasks 的示例及其翻译为 中文

These ensemble models often achieve very good performance on binary classification tasks.
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。

Some of these are classification tasks, some are prediction tasks, and many more.
其中一些是分类任务，一些是预测任务，还有许多其他任务。

This works very well for specific problems and, in many cases, helps automate classification tasks.
这样做非常适合于一些特定的问题，在许多情况下可以帮助完成自动分类任务。

Users can solve various classification tasks without the tedious manual adjustment of operators.
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。

Random forest is a machine learning method that is capable of performing both regression and classification tasks.
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。

It's been shown to work well in classification tasks and trains faster than sigmoid or tanh.
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。

For the first time, computers are able to perform some(narrowly defined) visual classification tasks better than people.
计算机首次能够比人类更好地执行一些视觉分类任务。

Results on a suite of 8 large text classification tasks show better performance than more shallow networks.
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。

For the first time, computers are able to perform some(narrowly defined) visual classification tasks better than people.
计算机首次能够比人类更好地执行一些（狭义定义的）视觉分类任务。

While especially efficient for classification tasks, deep learning suffers from serious limits and it can fail in unpredictable ways.
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。

We present EDA: easy data augmentation techniques for boosting performance on text classification tasks.
我要向你介绍EDA（EasyDataAugmentation）：用于提升文本分类任务表现的简单数据增强技术。

In deep learning, a computer model learns to perform classification tasks directly from images, text, or sound.
在深度学习中，计算机模型直接从图像、文本或声音中学习执行分类任务。

Geirhos and his colleagues have shown that those local features are sufficient to allow a network to perform image classification tasks.
吉尔霍斯和他的同事已经证明，这些局部特征足以让网络执行图像分类任务。

Some metrics are essentially defined for binary classification tasks(e.g. f1_score, roc_auc_score).
一些metrics基本上是为binaryclassificationtasks（二分类任务）定义的(例如f1_score,roc_auc_score)。

Entropy Guided Transformation Learning: Algorithms and Applications(ETL) presents a machine learning algorithm for classification tasks.
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。

In basic classification tasks, each input is considered in isolation from all other inputs, and the set of labels is defined in advance.
在基本的分类任务中，每个输入被认为是与所有其它输入隔离的，并且标签集是预先定义的。

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.
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%。

The current world-leading algorithms are not performing significantly better than random on real world“real news vs. fake news” classification tasks.
目前世界领先的算法在现实世界的“真实新闻vs.虚假新闻”分类任务中的表现并没有明显好于随机的。

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.
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％。

Classification tasks for affected country Parties will be simple, the secretariat being in charge of applying more comprehensive classification criteria to the information contained in the national reports.
受影响国家缔约方的分类任务会很简单，秘书处负责对国家报告中所载资料适用更全面的分类标准。

Viewed through the lens of multi-task learning, a model trained on ImageNet learns a large number of binary classification tasks(one for each class).
通过多任务学习，在ImageNet上训练的模型可以学习大量的二进制分类任务（每个类一个）。

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.
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%。

This result won the 1st place on the ILSVRC 2015 classification task.
这个结果在ILSVRC2015分类任务上赢得了第一名。

In the classification task, the cross entropy loss function is commonly used.
对于分类任务，通常使用交叉熵损失函数。

We treat it as multi-class classification task.
我们现在将这个问题看作一个多类分类任务。

With the probabilistic framework the classification task is defined as follows.
根据概率，我们将分类任务的框架按如下定义。

This is the basic idea of a classification task in machine learning, where”classification” indicates that the data has discrete class labels.
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。

Most of the features from convolution and pooling layers may be good for the classification task, but combinations of those features might be even better.
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。