Research graph
References from Reconciling symbols and neural networks: evidence for a quasi-symbolic view. Local targets link to admitted publications; unresolved targets remain external evidence.
Physical symbol systems
1980 · External reference
Unresolved reference
2024 · External reference
Unresolved reference
1986 · External reference
Unresolved reference
External reference
Mastering the game of Go with deep neural networks and tree search
10.1038/nature16961 · 2016 · External reference
Unresolved reference
External reference
A logical calculus of the ideas immanent in nervous activity
10.1007/bf02478259 · 1943 · External reference
10.1145/130385.130432
10.1145/130385.130432 · External reference
What formal languages can transformers express? A survey
10.1162/tacl_a_00663 · 2024 · External reference
Connectionism and cognitive architecture: a critical analysis
10.1016/0010-0277(88)90031-5 · 1988 · External reference
Rethinking eliminative connectionism
10.1006/cogp.1998.0694 · 1998 · External reference
10.18653/v1/w18-0102
10.18653/v1/w18-0102 · External reference
The neural architecture of language: Integrative modeling converges on predictive processing
10.1073/pnas.2105646118 · 2021 · External reference
How can deep neural networks inform theory in psychological science?
10.1177/09637214241268098 · 2024 · External reference
On the proper treatment of connectionism
10.1017/s0140525x00052432 · 1988 · External reference
Neurocompositional computing: from the central paradox of cognition to a new generation of AI systems
2022 · External reference
Why concepts are (probably) vectors
10.1016/j.tics.2024.06.011 · 2024 · External reference
Unresolved reference
1982 · External reference
Whither symbols in the era of advanced neural networks?
2025 · External reference
Tensor product variable binding and the representation of symbolic structures in connectionist systems
10.1016/0004-3702(90)90007-m · 1990 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
Discovering the Compositional Structure of Vector Representations with Role Learning Networks
2020 · External reference
10.18653/v1/w16-2524
10.18653/v1/w16-2524 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
10.18653/v1/2024.naacl-long.281
10.18653/v1/2024.naacl-long.281 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
10.18653/v1/w16-2503
10.18653/v1/w16-2503 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
Unresolved reference
External reference
Unresolved reference
External reference
Under the hood: using diagnostic classifiers to investigate and improve how language models track agreement information
2018 · External reference
10.18653/v1/2021.conll-1.15
10.18653/v1/2021.conll-1.15 · External reference
Unresolved reference
External reference
Interventionist methods for interpreting deep neural networks
2024 · External reference
Break it down: evidence for structural compositionality in neural networks
10.52202/075280-1848 · 2023 · External reference
On the biology of a large language model
2025 · External reference
Unresolved reference
External reference
Finding alignments between interpretable causal variables and distributed neural representations
2024 · External reference
Learning transformer programs
10.52202/075280-2131 · 2023 · External reference
Unresolved reference
External reference
Human-like systematic generalization through a meta-learning neural network
10.1038/s41586-023-06668-3 · 2023 · External reference
Modeling rapid language learning by distilling Bayesian priors into artificial neural networks
10.1038/s41467-025-59957-y · 2025 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
Generalization without systematicity: on the compositional skills of sequence-to-sequence recurrent networks
2018 · External reference
10.18653/v1/2020.emnlp-main.731
10.18653/v1/2020.emnlp-main.731 · External reference
Evaluating the robustness of analogical reasoning in large language models
2025 · External reference
Language models, like humans, show content effects on reasoning tasks
10.1093/pnasnexus/pgae233 · 2024 · External reference
Encoding interference effects support self-organized sentence processing
10.1016/j.cogpsych.2020.101356 · 2021 · External reference
Unresolved reference
External reference
Gradient symbolic representations in grammar: The case of French liaison
2016 · External reference
The present status of the innateness controversy
1981 · External reference
Unresolved reference
External reference
Unresolved reference
External reference
Characterizing the role of similarity in the property inferences of language models
2025 · External reference
Rethinking eliminative connectionism
10.1006/cogp.1998.0694 · ExternalCitation · doi-reference
A logical calculus of the ideas immanent in nervous activity
10.1007/bf02478259 · ExternalCitation · doi-reference
Tensor product variable binding and the representation of symbolic structures in connectionist systems
10.1016/0004-3702(90)90007-m · ExternalCitation · doi-reference
Connectionism and cognitive architecture: a critical analysis
10.1016/0010-0277(88)90031-5 · ExternalCitation · doi-reference
Encoding interference effects support self-organized sentence processing
10.1016/j.cogpsych.2020.101356 · ExternalCitation · doi-reference
Why concepts are (probably) vectors
10.1016/j.tics.2024.06.011 · ExternalCitation · doi-reference
On the proper treatment of connectionism
10.1017/s0140525x00052432 · ExternalCitation · doi-reference
Mastering the game of Go with deep neural networks and tree search
10.1038/nature16961 · ExternalCitation · doi-reference
Modeling rapid language learning by distilling Bayesian priors into artificial neural networks
10.1038/s41467-025-59957-y · ExternalCitation · doi-reference
Human-like systematic generalization through a meta-learning neural network
10.1038/s41586-023-06668-3 · ExternalCitation · doi-reference
The neural architecture of language: Integrative modeling converges on predictive processing
10.1073/pnas.2105646118 · ExternalCitation · doi-reference
Language models, like humans, show content effects on reasoning tasks
10.1093/pnasnexus/pgae233 · ExternalCitation · doi-reference
10.1145/130385.130432
10.1145/130385.130432 · ExternalCitation · doi-reference
What formal languages can transformers express? A survey
10.1162/tacl_a_00663 · ExternalCitation · doi-reference
How can deep neural networks inform theory in psychological science?
10.1177/09637214241268098 · ExternalCitation · doi-reference
10.18653/v1/2020.emnlp-main.731
10.18653/v1/2020.emnlp-main.731 · ExternalCitation · doi-reference
10.18653/v1/2021.conll-1.15
10.18653/v1/2021.conll-1.15 · ExternalCitation · doi-reference
10.18653/v1/2024.naacl-long.281
10.18653/v1/2024.naacl-long.281 · ExternalCitation · doi-reference
10.18653/v1/w16-2503
10.18653/v1/w16-2503 · ExternalCitation · doi-reference
10.18653/v1/w16-2524
10.18653/v1/w16-2524 · ExternalCitation · doi-reference
10.18653/v1/w18-0102
10.18653/v1/w18-0102 · ExternalCitation · doi-reference
Break it down: evidence for structural compositionality in neural networks
10.52202/075280-1848 · ExternalCitation · doi-reference
Learning transformer programs
10.52202/075280-2131 · ExternalCitation · doi-reference
