A rational account of pedagogical reasoning: teaching by, and learning from, examples.

By Patrick Shafto, Noah D. Goodman, T. Griffiths. 2014

300 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Developmental and Educational Psychology

How researchers see this paper

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

In Artificial Intelligence

In Developmental and Educational Psychology

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “…to compare, and (3) alternate training methods (e.g., Goyal et al., 2016) in which the same system is trained on different data sets to understand how it is using information; providing counter-examples (e.g., Shafto and Goodman, 2008; Shafto, Goodman, and Griffiths, 2014; Nguyen et al., 2015).”
Learning to Make Analogies by Contrasting Abstract Relational Structure (2019, positive): “The experiments there show that, in such cases, we might still achieve notable improvements in generalization via methods that learn to play the role of teacher by presenting alternatives to the main (student) model, as per Shafto et al. (2014).”
Interpretable and Pedagogical Examples (2017, methodology): “The intuitive strategy that human teachers tend to use is to pick opposite corners of the rectangle (Shafto et al., 2012; 2014).”
The Social Bayesian Brain: Does Mentalizing Make a Difference When We Learn? (2014, background): “Among the existing literature, the closest example to our work is [12], which shows that learners who know they are being explicitly taught (by a teacher) learn more from the data than when assuming otherwise.”
Teaching with Rewards and Punishments: Reinforcement or Communication? (2015, background): “In contrast, peoples’ understanding of communicative intent when learning new concepts from examples (Sperber & Wilson, 1986; Csibra & Gergely, 2009; Shafto et al., 2014) suggests an action-feedback model in which teachers expect learners to treat responses communicatively or as commentary about an…”
Pragmatic-Pedagogic Value Alignment (2017, methodology): “This framework can predict complex behaviors observed in human teaching-learning interactions, in which pedagogical utterances and pragmatic interpretations permit efficient communication [7].”
Learning to Teach (2018, background): “Furthermore, another literature called ‘pedagogical teaching’ (Shafto et al., 2014), especially its application to inverse reinforcement learning (IRL) (Ho et al., 2016) is much closer to our setting in that the teacher adjusts its behavior in order to facilitate student learning, by communicating…”
An Overview of Machine Teaching (2018, background): “This has lead to automated teaching approaches that select examples for a learner who assumes a helpful teacher [36].”
Showing versus doing: Teaching by demonstration (2016, methodology): “Our model draws on two approaches: IRL [2] and Bayesian models of teaching by example [14].”
A large-scale benchmark for few-shot program induction and synthesis (2021, background): “Humans actively use the knowledge that a teacher is giving them instructive examples to update their priors more effectively (Shafto et al., 2014).”
Learning to Teach with Dynamic Loss Functions (2018, background): “Furthermore there are research on pedagogical teaching inspired from cognitive science [44, 23, 39] in which a teacher module is responsible for providing informative examples to the learner for the sake of understanding a concept rapidly.”
Toward a general, scaleable framework for Bayesian teaching with applications to topic models (2016, background): “(2)For example, a document d = [2, 1, 2, 1, 3, 2, 1, 2, 2, 2] with counts [n1, n2, n3] = [3, 6, 1] would have the barycenter coordinates (0.”