Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378473764> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4378473764 abstract "Humans can learn languages from remarkably little experience. Developing computational models that explain this ability has been a major challenge in cognitive science. Bayesian models that build in strong inductive biases - factors that guide generalization - have been successful at explaining how humans might generalize from few examples in controlled settings but are usually too restrictive to be tractably applied to more naturalistic data. By contrast, neural networks have flexible representations that allow them to learn well from naturalistic data but require many more examples than humans receive. We show that learning from limited naturalistic data is possible with an approach that combines the strong inductive biases of a Bayesian model with the flexible representations of a neural network. This approach works by distilling a Bayesian model's biases into a neural network. Like a Bayesian model, the resulting system can learn formal linguistic patterns from a small number of examples. Like a neural network, it can also learn aspects of English syntax from a corpus of natural language - and it outperforms a standard neural network at acquiring the linguistic phenomena of recursion and priming. Bridging the divide between Bayesian models and neural networks makes it possible to handle a broader range of learning scenarios than either approach can handle on its own." @default.
- W4378473764 created "2023-05-27" @default.
- W4378473764 creator A5003082850 @default.
- W4378473764 creator A5077079119 @default.
- W4378473764 date "2023-05-24" @default.
- W4378473764 modified "2023-09-25" @default.
- W4378473764 title "Modeling rapid language learning by distilling Bayesian priors into artificial neural networks" @default.
- W4378473764 doi "https://doi.org/10.48550/arxiv.2305.14701" @default.
- W4378473764 hasPublicationYear "2023" @default.
- W4378473764 type Work @default.
- W4378473764 citedByCount "0" @default.
- W4378473764 crossrefType "posted-content" @default.
- W4378473764 hasAuthorship W4378473764A5003082850 @default.
- W4378473764 hasAuthorship W4378473764A5077079119 @default.
- W4378473764 hasBestOaLocation W43784737641 @default.
- W4378473764 hasConcept C107673813 @default.
- W4378473764 hasConcept C11413529 @default.
- W4378473764 hasConcept C119857082 @default.
- W4378473764 hasConcept C134306372 @default.
- W4378473764 hasConcept C154945302 @default.
- W4378473764 hasConcept C160234255 @default.
- W4378473764 hasConcept C162324750 @default.
- W4378473764 hasConcept C168773036 @default.
- W4378473764 hasConcept C177148314 @default.
- W4378473764 hasConcept C187736073 @default.
- W4378473764 hasConcept C197352929 @default.
- W4378473764 hasConcept C2780451532 @default.
- W4378473764 hasConcept C28006648 @default.
- W4378473764 hasConcept C33724603 @default.
- W4378473764 hasConcept C33923547 @default.
- W4378473764 hasConcept C41008148 @default.
- W4378473764 hasConcept C50644808 @default.
- W4378473764 hasConcept C60048249 @default.
- W4378473764 hasConcept C71983512 @default.
- W4378473764 hasConceptScore W4378473764C107673813 @default.
- W4378473764 hasConceptScore W4378473764C11413529 @default.
- W4378473764 hasConceptScore W4378473764C119857082 @default.
- W4378473764 hasConceptScore W4378473764C134306372 @default.
- W4378473764 hasConceptScore W4378473764C154945302 @default.
- W4378473764 hasConceptScore W4378473764C160234255 @default.
- W4378473764 hasConceptScore W4378473764C162324750 @default.
- W4378473764 hasConceptScore W4378473764C168773036 @default.
- W4378473764 hasConceptScore W4378473764C177148314 @default.
- W4378473764 hasConceptScore W4378473764C187736073 @default.
- W4378473764 hasConceptScore W4378473764C197352929 @default.
- W4378473764 hasConceptScore W4378473764C2780451532 @default.
- W4378473764 hasConceptScore W4378473764C28006648 @default.
- W4378473764 hasConceptScore W4378473764C33724603 @default.
- W4378473764 hasConceptScore W4378473764C33923547 @default.
- W4378473764 hasConceptScore W4378473764C41008148 @default.
- W4378473764 hasConceptScore W4378473764C50644808 @default.
- W4378473764 hasConceptScore W4378473764C60048249 @default.
- W4378473764 hasConceptScore W4378473764C71983512 @default.
- W4378473764 hasLocation W43784737641 @default.
- W4378473764 hasOpenAccess W4378473764 @default.
- W4378473764 hasPrimaryLocation W43784737641 @default.
- W4378473764 hasRelatedWork W1599577651 @default.
- W4378473764 hasRelatedWork W1855426618 @default.
- W4378473764 hasRelatedWork W2326372119 @default.
- W4378473764 hasRelatedWork W2352852554 @default.
- W4378473764 hasRelatedWork W2364992962 @default.
- W4378473764 hasRelatedWork W2902480041 @default.
- W4378473764 hasRelatedWork W2902946190 @default.
- W4378473764 hasRelatedWork W2963058055 @default.
- W4378473764 hasRelatedWork W4210723310 @default.
- W4378473764 hasRelatedWork W96862169 @default.
- W4378473764 isParatext "false" @default.
- W4378473764 isRetracted "false" @default.
- W4378473764 workType "article" @default.