A Bayesian framework for concept learning

By Josh Tenenbaum. 1999

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

Recasting Gradient-Based Meta-Learning as Hierarchical Bayes (2018, background): “Meta-learning and few-shot learning have a long history in hierarchical Bayesian modeling ( e.g., Tenenbaum, 1999; Fei-Fei et al., 2003; Lawrence & Platt, 2004; Yu et al., 2005; Gao et al., 2008; Daumé III, 2009; Wan et al., 2012).”
Probabilistic Model-Agnostic Meta-Learning (2018, methodology): “Hierarchical Bayesian models are a long-standing approach for few-shot learning that naturally allow for the ability to reason about uncertainty over functions [39, 7, 25, 43, 12, 4, 41].”
Bayesian Model-Agnostic Meta-Learning (2018, background): “There have been many studies in the past that formulate meta-learning and learning-to-learn from a probabilistic modeling perspective (Tenenbaum, 1999; Fe-Fei et al., 2003; Lawrence & Platt, 2004; Daumé III, 2009).”
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables (2019, methodology): “Hierarchical Bayesian models have been used to model few-shot learning (Fei-Fei et al., 2003; Tenenbaum, 1999), including approaches that perform gradient-based adaptation (Grant et al., 2018; Yoon et al., 2018).”
Infants consider both the sample and the sampling process in inductive generalization (2010, background): “As the names indicate, weak sampling is a less powerful constraint on induction than strong sampling (9).”
Generative Models of Visually Grounded Imagination (2017, background): “One of the key challenges in concept learning is to understand “how far” to generalize in the concept hierarchy given a limited number of positive examples (Tenenbaum, 1999).”
On Completeness-aware Concept-Based Explanations in Deep Neural Networks (2019, background): “In contrast, human reasoning often comprise “concept-based thinking,” extracting similarities from numerous examples and grouping them systematically based on their resemblance [3, 4].”
On Concept-Based Explanations in Deep Neural Networks (2019, background): “shown to play an essential role in human minds for making generalizations [3, 28].”
Meta-Learning without Memorization (2019, methodology): “Our derivation uses a Bayesian interpretation of meta-learning (Tenenbaum, 1999; Fei-Fei et al., 2003; Edwards & Storkey, 2016; Grant et al., 2018; Gordon et al., 2018; Finn et al., 2018; Kim et al., 2018; Harrison et al., 2018).”
On the role of locality in learning stress patterns* (2009, methodology): “In other words, in the P&P and OT frameworks, the proposed learning mechanisms operate over the structure provided by the framework, and not any inherent structure that may exist in the hypothesis space itself.2 The approach taken here also differs from the recent work in probabilistic-based learnin”
Troubles with Bayesianism: An introduction to the psychological immune system (2018, background): “A decade or so ago, only a handful of cognitive scientists had attempted to explain mental processing by Bayesian lights (e.g., Glymour, 2003; Gopnik et al., 2004; Tenenbaum, 1999).”
Generalization, similarity, and Bayesian inference. (2001, unknown): “Much of our proposal for extending Shepard's theory to the cases of multiple examples and arbitrary stimulus structures has already been introduced in other papers (Griffiths & Tenenbaum, 2000; Tenenbaum, 1997, 1999a, 1999b; Tenenbaum & Xu, 2000).”
Word learning as Bayesian inference. (2007, methodology): “The Bayesian Framework Our model is formulated within the Bayesian framework for concept learning and generalization introduced by Tenenbaum and his colleagues (Tenenbaum, 1999; Tenenbaum & Griffiths, 2001; Tenenbaum, Griffiths, & Kemp, 2006).”
Précis of Bayesian Rationality: The Probabilistic Approach to Human Reasoning (2009, background): “Moreover, the extensive empirical testing of these models (Green & Over 1997; 2000; McKenzie & Mikkelsen 2000; 2007; McKenzie et al. 2001; Nelson 2005; Oaksford & Moussakowski 2004; Oaksford & Wakefield 2003; Oaksford et al. 1999; 2000; Tenenbaum 1999) should allay concerns that rational analysis pr”