Iterative Machine Teaching
Iterative Machine Teaching
复制标题
DOI：
--
复制
发表时间：
2017-05
期刊：
影响因子：
--
通讯作者：
Weiyang Liu;Bo Dai;Ahmad Humayun;C. Tay;Chen Yu;Linda B. Smith;James M. Rehg;Le Song
中科院分区：
文献类型：
--
作者：
Weiyang Liu;Bo Dai;Ahmad Humayun;C. Tay;Chen Yu;Linda B. Smith;James M. Rehg;Le Song
在本文中，我们考虑了机器教学的问题，这是机器学习的反问题。与将学习者视为批处理算法的传统机器教学不同，我们研究了一个新的范式，学习者使用迭代算法，而教师可以根据学习者的当前表现依次，智能地喂食示例。我们表明，在迭代案例中的教学复杂性与批处理案例的教学复杂性大不相同。我们的迭代机械教学并没有为学习者建造最小的培训集，而是专注于在学习者模型中实现快速融合。根据教师从学习者模型中获得的信息水平，我们设计了教学算法，这些算法可以证明可以减少教学示例的数量并获得比没有教师的学习更快的融合。我们还通过有关不同数据分布和真实图像数据集的广泛实验来验证我们的理论发现。
In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learner. We show that the teaching complexity in the iterative case is very different from that in the batch case. Instead of constructing a minimal training set for learners, our iterative machine teaching focuses on achieving fast convergence in the learner model. Depending on the level of information the teacher has from the learner model, we design teaching algorithms which can provably reduce the number of teaching examples and achieve faster convergence than learning without teachers. We also validate our theoretical findings with extensive experiments on different data distribution and real image datasets.