The article discusses the limitations of artificial neural networks (ANNs) in modeling cognitive structures critical for language and thought. It highlights a long-standing debate over whether ANNs can adequately capture the features of cognition that traditional symbolic architectures address. This dilemma poses a challenge: if ANNs can reflect structure-sensitive behaviors, they do so by mimicking classical rule-based computations, raising questions about their explanatory power in cognitive modeling. Ultimately, the article situates the capabilities of ANNs within broader philosophical inquiries about language and thought connectivity.
According to a long-standing critique of the connectionist research program, artificial neural networks would be fundamentally incapable of accounting for the core structure-sensitive features of cognition.
This critique centers on a dilemma: either ANNs fail to capture the features of cognition that can be readily accounted for in a classical symbolic architecture.
Collection
[
|
...
]