.png){kind=icon}
.png){kind=icon}
Return
Is human compositionality meta-learned?
.png){kind=icon}
PRE
AI
DOI：10.1017/S0140525X24000189.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recent studies suggest that meta-learning may provide an original solution to an enduring puzzle about whether neural net-works can explain compositionality-in particular, by raising the prospect that compositionality can be understood as an emergent property of an inner-loop learning algorithm. Weelaborate on this hypothesis and consider its empirical predictions regarding the neural mechanisms and development of human compositionality.
Keywords:
PREFRONTAL CORTEX
COGNITIVE CONTROL
MECHANISMS
RULES