Timezone: »
Machine learning systems often do not share the same inductive biases as humans and, as a result, extrapolate or generalize in ways that are inconsistent with our expectations. The trade-off between exemplar- and rule-based generalization has been studied extensively in cognitive psychology; in this work, we present a protocol inspired by these experimental approaches to probe the inductive biases that control this trade-off in category-learning systems such as artificial neural networks. We isolate two such inductive biases: feature-level bias (differences in which features are more readily learned) and exemplar-vs-rule bias (differences in how these learned features are used for generalization of category labels). We find that standard neural network models are feature-biased and have a propensity towards exemplar-based extrapolation; we discuss the implications of these findings for machine-learning research on data augmentation, fairness, and systematic generalization.
Author Information
Ishita Dasgupta (DeepMind)
Erin Grant (UC Berkeley)
Thomas Griffiths (Princeton University)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: Distinguishing rule- and exemplar-based generalization in learning systems »
Tue. Jul 19th 09:10 -- 09:15 PM Room Room 301 - 303
More from the Same Authors
-
2022 : Predicting generalization with degrees of freedom in neural networks »
Erin Grant · Yan Wu -
2022 : Predicting Human Similarity Judgments Using Large Language Models »
Raja Marjieh · Ilia Sucholutsky · Theodore R Sumers · Nori Jacoby · Thomas Griffiths · Thomas Griffiths -
2023 Poster: Analyzing Diffusion as Serial Reproduction »
Raja Marjieh · Ilia Sucholutsky · Thomas Langlois · Nori Jacoby · Thomas Griffiths -
2021 Poster: Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment »
Michael Chang · Sid Kaushik · Sergey Levine · Thomas Griffiths -
2021 Oral: Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment »
Michael Chang · Sid Kaushik · Sergey Levine · Thomas Griffiths -
2020 : Invited Talk 2: Prof. Tom Griffiths from Princeton University »
Thomas Griffiths -
2020 Poster: Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions »
Michael Chang · Sid Kaushik · S. Matthew Weinberg · Thomas Griffiths · Sergey Levine -
2019 Poster: Cognitive model priors for predicting human decisions »
Joshua C Peterson · David D Bourgin · Daniel Reichman · Thomas Griffiths · Stuart Russell -
2019 Oral: Cognitive model priors for predicting human decisions »
Joshua C Peterson · David D Bourgin · Daniel Reichman · Thomas Griffiths · Stuart Russell