Optimal Teaching for Limited-Capacity Human Learners

By Kaustubh R. Patil, Xiaojin Zhu, Lukasz Kopec, Bradley C. Love. 2014

75 citations recorded by the source corpus.

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

Using Machine Teaching to Identify Optimal Training-Set Attacks on Machine Learners (2015, methodology): “Our training-set attack formulation is closely related to machine teaching (Zhu 2013; Patil et al. 2014).”
The Teaching Dimension of Linear Learners (2015, unknown): “training set (Patil et al., 2014).”
Security and Privacy Issues in Deep Learning (2018, background): “Physical world AE [Kurakin et al. 2016a] Policy induction attack [Behzadan and Munir 2017] Human AE [Elsayed et al. 2018] Poisoning Poisoning attack against SVM [Biggio et al. 2012] Optimal teaching [Patil et al. 2014] Optimal Training-set attacks [Mei and Zhu 2015] Back-gradient optimization [Munoz”
Teacher Improves Learning by Selecting a Training Subset (2018, background): “Machine teaching applications include education [14, 33, 39, 27, 13, 34], computer security [2, 1, 32], and interactive machine learning [40, 12, 24].”
Teaching Multiple Concepts to Forgetful Learners (2018, background): “[23, 21] have studied the problem of concept learning and machine teaching when learner has “limited-capacity" in terms of retrieving exemplars in memory during the decision-making process.”
Teaching Multiple Concepts to a Forgetful Learner (2018, background): “[23, 21] have studied the problem of concept learning and machine teaching when learner has “limited-capacity" in terms of retrieving exemplars in memory during the decision-making process.”
An Optimal Control Approach to Sequential Machine Teaching (2018, background): “In education systems, a teacher may optimize the training curriculum to enhance student (modeled as a learning algorithm) learning (Sen et al., 2018; Patil et al., 2014).”
Toward a general, scaleable framework for Bayesian teaching with applications to topic models (2016, background): “The question of how to model teaching has also appeared across literatures: cognitive scientists have proposed and investigated probabilistic models of optimal example selection [4–7]; algorithmic teaching researchers have proposed deterministic methods to select examples that rule out confusable co”
An Overview of Machine Teaching (2018, background): “The learner can take a variety of forms, including version space learners for the theoretical study of Teaching Dimension (to be discussed later) [18], Bayesian learners [47], deep neural networks, or cognitive models which model how humans learn [33].”
Optimization Models for Machine Learning: A Survey (2019, methodology): “In [217], a method is proposed for the Bayesian learners, while [174] focuses on Generalized Context Model learners.”
Becoming the expert - interactive multi-class machine teaching (2015, methodology): “The majority of previous work in Machine Teaching has focused on non-interactive teaching, where one teaching set is computed ofﬂine, independent of feedback from each student [39, 33].”