arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.03643cs.LGcs.AI
收藏

学有所教

Learning to Teach

University of Science and Technology of China(中国科学技术大学);Microsoft Research Asia(微软亚洲研究院);Microsoft Research(微软研究院)

Yang Fan, Fei Tian, Tao Qin, Xiang-Yang Li, Tie-Yan Liu

摘要:

教学在我们的社会中起着非常重要的作用,通过传播人类知识和教育我们的下一代。一个好的老师会根据学生的学习行为选择合适的教材,影响合适的方法,并设置有针对性的考试。然而在人工智能领域,人们还没有充分挖掘教学的作用,最关注的还是机器\emph{learning}。本文认为,在教学中应给予同等的重视,甚至更多,并应使用一个优化框架(而不是数学),以获得良好的教学策略。我们称这种方法为“学会教学”。在该方法中,两个智能代理相互交互:学生模型(对应于传统机器学习算法中的学习者)和教师模型(确定适当的数据,损失函数和假设空间,以促进学生模型的训练)。教师模型利用学生模型的反馈,通过强化学习优化自身的教学策略,实现师生协同进化。为了证明我们提出的方法的实用价值,我们以深度神经网络(DNN)的训练为例,并表明通过使用学习教学技术,我们能够使用更少的训练数据和更少的迭代来实现几乎相同的精度,用于不同种类的DNN模型(例如,多层感知器、卷积神经网络和循环神经网络)在各种机器学习任务(例如,图像分类和文本理解)。

英文摘要:

Teaching plays a very important role in our society, by spreading human knowledge and educating our next generations. A good teacher will select appropriate teaching materials, impact suitable methodologies, and set up targeted examinations, according to the learning behaviors of the students. In the field of artificial intelligence, however, one has not fully explored the role of teaching, and pays most attention to machine \emph{learning}. In this paper, we argue that equal attention, if not more, should be paid to teaching, and furthermore, an optimization framework (instead of heuristics) should be used to obtain good teaching strategies. We call this approach `learning to teach'. In the approach, two intelligent agents interact with each other: a student model (which corresponds to the learner in traditional machine learning algorithms), and a teacher model (which determines the appropriate data, loss function, and hypothesis space to facilitate the training of the student model). The teacher model leverages the feedback from the student model to optimize its own teaching strategies by means of reinforcement learning, so as to achieve teacher-student co-evolution. To demonstrate the practical value of our proposed approach, we take the training of deep neural networks (DNN) as an example, and show that by using the learning to teach techniques, we are able to use much less training data and fewer iterations to achieve almost the same accuracy for different kinds of DNN models (e.g., multi-layer perceptron, convolutional neural networks and recurrent neural networks) under various machine learning tasks (e.g., image classification and text understanding).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑