What is the translation of " MULTI-TASK LEARNING " in Chinese?

• 多任务学习

Examples of using Multi-task learning in English and their translations into Chinese

Lesson 20: When to use multi-task learning?
第20课：什么时候使用多任务学习？?

In multi-task learning, you train a model on different tasks at the same time.
在多任务学习中，你可以同时在不同的任务上对一个模型进行训练。

Furthermore establish upper bounds for using the group lasso in multi-task learning.
进一步使用组合lasso在多任务学习中建立上限。

We perform multi-task learning and predict the absolute and relative poses simultaneously.
我们执行多任务学习并同时预测绝对和相对。

Know how to apply end-to-end learning, transfer learning, and multi-task learning.
知道如何应用端到端学习、迁移学习以及多任务学习.

This approach is called Multi-Task Learning(MTL) and will be the topic of this blog post.
这种方法被称为多任务学习（MTL），这正是本文的主题。

Understand when to use end-to-end learning, transfer learning and multi-task learning.
知道如何应用端到端学习、迁移学习以及多任务学习.

Ng thinks that transfer learning and multi-task learning are both really good research direction.
在研究上，吴恩达认为迁移学习和多任务学习是很好的研究方向。

Multi-task learning is a general method for sharing parameters between models that are trained on multiple tasks.
多任务学习是在多个任务上训练的模型之间共享参数的一种通用方法。

Figure 7: Uncertainty-based loss function weighting for multi-task learning(Kendall et al., 2017).
图7：用于多任务学习的基于不确定性的损失函数加权（Kendall等人，2017）。

Here we propose a multi-task learning(MTL)-based regularization framework for cardiac MR image segmentation.
在这里，我们提出了一个基于多任务学习（MTL）的心脏MR图像分割正则化框架。

The 2008 paper by Collobert and Weston proved influential beyond its use of multi-task learning.
年，Collobert和Weston共同撰写的论文对多任务学习之外的其他应用还产生了一定的影响。

Intuitively, multi-task learning encourages the models to learn representations that are useful for many tasks.
直观地说，多任务学习鼓励模型学习对许多任务有用的表述。

Understand how to apply end-to-end learning, multi-task learning, and transfer learning..
知道如何应用端到端学习、迁移学习以及多任务学习.

This major breakthrough in NLP takes advantage of a new innovation called“Continual Incremental Multi-Task Learning”.
NLP的这一重大突破利用了一项被称为“连续增量式多任务学习”的创新技术。

If additional data is available, multi-task learning(MTL) can often be used to improve performance on the target task.
如果有额外的数据，多任务学习（MTL）通常可用于在目标任务中提升性能。

Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off.
多任务学习的本质是多目标问题，因为不同的人物之间可能会冲突，所以需要进行权衡。

From a research perspective, I think that transfer learning and multi-task learning is one of the areas that I would love to figure out.
答：从研究角度来看，我认为迁移学习和多任务学习是我需要探索的领域之一。

For example, in multi-task learning, a single model solves multiple tasks, such as a deep model that has different output nodes for different tasks.
例如，在多任务学习中，一个模型可以完成多项任务，例如针对不同任务具有不同输出节点的深度模型。

From a research perspective, I think that transfer learning and multi-task learning is one of the areas that I would love to figure out.
答：从研究角度出发，我认为迁移学习和多任务学习是我想试着解决的问题之一。

Finally, we can motivate multi-task learning from a machine learning point of view: We can view multi-task learning as a form of inductive transfer.
最后，从机器学习的角度：我们可以将多任务学习看作归纳转移的一种形式。

In this overview, I have reviewed both the history of literature in multi-task learning as well as more recent work on MTL for Deep Learning..
在本篇概述中，我们回顾了多任务学习的发展历程，以及最近的深度学习MTL的研究。

We can motivate multi-task learning in different ways: Biologically, we can see multi-task learning as being inspired by human learning..
多任务学习的动机有不同的方式：从生物学的角度，多任务学习可以看作是受到人类学习的启发。

Transfer learning is connected to problems like multi-task learning and concept drift and isn't exclusively a subject of study for deep learning..
迁移学习还与多任务学习和概念漂移等问题有关，它并不完全是深度学习的一个研究领域。

In this paper, we explicitly cast multi-task learning as multi-objective optimization, with the overall objective of finding a Pareto optimal solution.
在本文中，我们将多任务学习看作多目标优化，其总体目标就是找到帕累托最优解。

Advances in sentiment analysis, question answering, and joint multi-task learning are making it possible for AI to truly understand humans and the way we communicate….
情感分析、问题回答和联合多任务学习方面的进步使AI能够真正理解人类以及我们的交流方式。

Propose a Bayesian neural network for multi-task learning by placing a prior on the model parameters to encourage similar parameters across tasks.
文献[22]提出了一个用于多任务学习的贝叶斯神经网络，通过对模型参数加先验来鼓励不同任务参数相似。

Advances in sentiment analysis, question answering, and joint multi-task learning are making it possible for AI to truly understand humans and the way we communicate.
在情感分析、问答系统和联合多任务学习方面的进步，是人工智能得以能够真正理解人类和我们沟通的方式。

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）。

Another related line of work is multi-task learning, where several tasks are learned jointly(Caruna 1993; Augenstein, Vlachos, and Maynard 2015).
另一个相关的研究领域是多任务学习，其中几个任务是联合学习的（Caruna1993;Augenstein,Vlachos,andMaynard2015）。