Compositionality Decomposed¶
Hupkes, D., Dankers, Mul, & Bruni, E. (2020). Compositionality Decomposed: How Do Neural Networks Generalise?. Journal of Artificial Intelligence Research, 757-795.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Compositionality
- Hupkes et al. (2020) investigate compositionality in decomposed neural networks, showing that explicit architectural priors for compositionality improve generalization.
This sourceDefines and tests five aspects of compositional generalization in neural networks; supports D22-233. NOTE: the .md mis-lists authors as 'Hupkes, D., Veldhoen, S., & Zuidema, W.' — that is a different (2018) paper; the 2020 JAIR paper's authors are Hupkes, Dankers, Mul & Bruni.
- Hupkes et al. (2020) investigate compositionality in decomposed neural networks, showing that explicit architectural priors for compositionality improve generalization.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:6dd1849f257e · see in the full table