Thesisgreen1999

A Bayesian framework for concept learning

100 citations0/0 files storedDSpace@MIT (Massachusetts Institute of Technology)

No readable copy stored yet — this record is metadata only.

Categorization, perception, and language Bayesian Modeling and Causal Inference Machine Learning and Algorithms

Abstract

Human concept learning presents a version of the classic problem of induction, which is made particularly difficult by the combination of two requirements: the need to learn from a rich (i.e. nested and overlapping) vocabulary of possible concepts and the need to be able to generalize concepts reasonably from only a few positive examples. I begin this thesis by considering a simple number concept game as a concrete illustration of this ability. On this task, human learners can with reasonable confidence lock in on one out of a billion billion billion logically possible concepts, after seeing only four positive examples of the concept, and can generalize informatively after seeing just a single example. Neither of the two classic approaches to inductive inference -- hypothesis testing in a constrained space of possible rules and computing similarity to the observed examples -- can provide a complete picture of how people generalize concepts in even this simple setting. This thesis prop...

Citations in this library

Stored only when both papers are in the corpus — 100 citations exist upstream.

References

1891The Principles of Psychology 1739A Treatise of Human Nature 1977Features of similarity.1983Extensional versus intuitive reasoning: The conjunction fallacy in probability judgment.1985Conceptual Change in Childhood 1996The empirical case for two systems of reasoning.1983Knowledge and the Flow of Information.1971Belief in the law of small numbers.

Cited by

2009On the role of locality in learning stress patterns 2008Using Category Structures to Test Iterated Learning as a Method for Identifying Inductive Biases 1999Rules and Similarity in Concept Learning 2011Sampling Assumptions in Inductive Generalization 2022One model for the learning of language 2020A bird’s-eye view of naming game dynamics: From trait competition to Bayesian inference

Imported from OpenAlex (CC0) — nothing here is generated.