A rule-based decision is made on the basis of minimal features that support the cate- gory boundary (e.g., Ashby & Townsend, 1986), while an exemplar-based decision-maker generalizes on the basis of similarity to category exemplars (e.g., Shepard & Chang, 1963), invoking many or all features that underlie a category.
Oct 8, 2021 · We isolate two such inductive biases: feature-level bias (differences in which features are more readily learned) and exemplar or rule bias ( ...
Jan 28, 2022 · The results confirm that generalized linear model favors rule-based generalization while Gaussian process favors exemplar-based generalization.
We make normative statements about when a model should be rule-based or exemplar-based. (compositional generalization and long-tailed distributions, resp.).
Sep 5, 2024 · We present empirical results across a range of models and across both expository and real-world image and language domains. We demonstrate that ...
Code for our 2022 ICML paper "Distinguishing rule- and exemplar-based generalization in learning systems." arxiv.org/abs/2110.04328. License. MIT license.
In this paper, we compare systems learning concepts represented in this form with those which learn concepts represented by decision rules, such as the ID3 and ...
Missing: Distinguishing generalization
We aim to clarify the distinction between the two representational schemes, and compare how systems based on the different schemes address the problem of ...
Missing: Distinguishing | Show results with:Distinguishing
Distinguishing Rule and Exemplar-based Generalization in Learning Systems · ISHITA DASGUPTA et. al. (Go back to Expert Review). Related Experts. Rank, Expert ...
Psychological theories of categorization generally focus on either rule- or exemplar-based explanations. We present 2 experiments that show evidence of both ...