Teachability in computational learning

By Ayumi Shinohara. 1990

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Dataset Distillation (2018, methodology): “Our method is also related to the theoretical concept of teaching dimension, which speciﬁes the size of dataset necessary to teach a target model to a learner (Shinohara & Miyano, 1991; Goldman & Kearns, 1995).”
Machine Teaching: An Inverse Problem to Machine Learning and an Approach Toward Optimal Education (2015, background): “The seminal notion of teaching dimension concerns the cardinality of the optimal teaching set (Goldman and Kearns 1995; Shinohara and Miyano 1991).”
Label Propagation via Teaching-to-Learn and Learning-to-Teach (2017, background): “The early works related to machine teaching mainly focus on the teaching dimension theory [23], [24].”
Teacher Improves Learning by Selecting a Training Subset (2018, background): “The theoretical study of machine teaching has focused on the teaching dimension, i.e. the minimum training set size needed to exactly teach a target concept θ ∗ [20, 38, 46, 18, 29, 45, 16, 44, 48, 9, 3, 4, 21, 31, 8, 7, 25, 5, 36, 23, 10].”
Recursive teaching dimension, VC-dimension and sample compression (2014, background): “It lower bounds not only the teaching dimension—the measure of information complexity in the “classical” teaching model (Goldman and Kearns, 1995; Shinohara and Miyano, 1991)— but also the information complexity of iterated optimal teaching (Balbach, 2008), which is often substantially smaller than…”
Teaching a black-box learner (2019, methodology): “Earlier theoretical work on teaching assumes both, such as the classic teaching dimension (Goldman & Kearns, 1995; Shinohara & Miyano, 1991), the recursive teaching dimen-sion (Zilles et al., 2011; Hu et al., 2017) and the preference-based teaching dimension (Gao et al., 2017).”
Complexity of Teaching by a Restricted Number of Examples (2009, methodology): “In this paper, we adopt the style assuming the worst case learner in the same way as the classical model [ SM91 , GK95].”
Optimization Models for Machine Learning: A Survey (2019, background): “The Teaching Dimension problem identifies the minimum size of a training set to correctly teach a model [105, 190].”
The Teaching Dimension of Linear Learners (2015, background): “How many training items are needed? This is the question addressed by the teaching dimension [13, 23].”
Measuring teachability using variants of the teaching dimension (2008, methodology): “To date, there is basically one formal teaching model, devised independently by Shinohara and Miyano [31], Goldman and Kearns [12], as well as Anthony, Brightwell, Cohen, and Shawe-Taylor [4].”
Recent Developments in Algorithmic Teaching (2009, methodology): “3 Note that a teaching set is also called key [32], discriminant [28] and witness set [25].”