2023
DOI: 10.1371/journal.pcbi.1011316
|View full text |Cite
|
Sign up to set email alerts
|

Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning

Sreejan Kumar,
Ishita Dasgupta,
Nathaniel D. Daw
et al.

Abstract: The ability to acquire abstract knowledge is a hallmark of human intelligence and is believed by many to be one of the core differences between humans and neural network models. Agents can be endowed with an inductive bias towards abstraction through meta-learning, where they are trained on a distribution of tasks that share some abstract structure that can be learned and applied. However, because neural networks are hard to interpret, it can be difficult to tell whether agents have learned the underlying abst… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 52 publications
0
1
0
Order By: Relevance
“…47 for a formal connection), although with the aid of neural networks for greater expressive power. Our research adds to a growing literature, reviewed previously 48 , on using meta-learning for understanding human [49][50][51] or human-like behaviour [52][53][54] . In our experiments, only MLC closely reproduced human behaviour with respect to both systematicity and biases, with the MLC ( joint) model best navigating the trade-off between these two blueprints of human linguistic behaviour.…”
Section: Discussionmentioning
confidence: 99%
“…47 for a formal connection), although with the aid of neural networks for greater expressive power. Our research adds to a growing literature, reviewed previously 48 , on using meta-learning for understanding human [49][50][51] or human-like behaviour [52][53][54] . In our experiments, only MLC closely reproduced human behaviour with respect to both systematicity and biases, with the MLC ( joint) model best navigating the trade-off between these two blueprints of human linguistic behaviour.…”
Section: Discussionmentioning
confidence: 99%