Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382318911> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4382318911 endingPage "12259" @default.
- W4382318911 startingPage "12252" @default.
- W4382318911 abstract "This paper develops a novel methodology to simultaneously learn a neural network and extract generalized logic rules. Different from prior neural-symbolic methods that require background knowledge and candidate logical rules to be provided, we aim to induce task semantics with minimal priors. This is achieved by a two-step learning framework that iterates between optimizing neural predictions of task labels and searching for a more accurate representation of the hidden task semantics. Notably, supervision works in both directions: (partially) induced task semantics guide the learning of the neural network and induced neural predictions admit an improved semantic representation. We demonstrate that our proposed framework is capable of achieving superior out-of-distribution generalization performance on two tasks: (i) learning multi-digit addition, where it is trained on short sequences of digits and tested on long sequences of digits; (ii) predicting the optimal action in the Tower of Hanoi, where the model is challenged to discover a policy independent of the number of disks in the puzzle." @default.
- W4382318911 created "2023-06-28" @default.
- W4382318911 creator A5009539513 @default.
- W4382318911 creator A5043925036 @default.
- W4382318911 creator A5057756881 @default.
- W4382318911 creator A5075080333 @default.
- W4382318911 date "2023-06-26" @default.
- W4382318911 modified "2023-09-23" @default.
- W4382318911 title "Out-of-Distribution Generalization by Neural-Symbolic Joint Training" @default.
- W4382318911 doi "https://doi.org/10.1609/aaai.v37i10.26444" @default.
- W4382318911 hasPublicationYear "2023" @default.
- W4382318911 type Work @default.
- W4382318911 citedByCount "0" @default.
- W4382318911 crossrefType "journal-article" @default.
- W4382318911 hasAuthorship W4382318911A5009539513 @default.
- W4382318911 hasAuthorship W4382318911A5043925036 @default.
- W4382318911 hasAuthorship W4382318911A5057756881 @default.
- W4382318911 hasAuthorship W4382318911A5075080333 @default.
- W4382318911 hasBestOaLocation W43823189111 @default.
- W4382318911 hasConcept C107673813 @default.
- W4382318911 hasConcept C119857082 @default.
- W4382318911 hasConcept C134306372 @default.
- W4382318911 hasConcept C140479938 @default.
- W4382318911 hasConcept C154945302 @default.
- W4382318911 hasConcept C162324750 @default.
- W4382318911 hasConcept C177148314 @default.
- W4382318911 hasConcept C17744445 @default.
- W4382318911 hasConcept C177769412 @default.
- W4382318911 hasConcept C184337299 @default.
- W4382318911 hasConcept C187736073 @default.
- W4382318911 hasConcept C199360897 @default.
- W4382318911 hasConcept C199539241 @default.
- W4382318911 hasConcept C204160518 @default.
- W4382318911 hasConcept C2776359362 @default.
- W4382318911 hasConcept C2780451532 @default.
- W4382318911 hasConcept C33923547 @default.
- W4382318911 hasConcept C41008148 @default.
- W4382318911 hasConcept C50644808 @default.
- W4382318911 hasConcept C94625758 @default.
- W4382318911 hasConceptScore W4382318911C107673813 @default.
- W4382318911 hasConceptScore W4382318911C119857082 @default.
- W4382318911 hasConceptScore W4382318911C134306372 @default.
- W4382318911 hasConceptScore W4382318911C140479938 @default.
- W4382318911 hasConceptScore W4382318911C154945302 @default.
- W4382318911 hasConceptScore W4382318911C162324750 @default.
- W4382318911 hasConceptScore W4382318911C177148314 @default.
- W4382318911 hasConceptScore W4382318911C17744445 @default.
- W4382318911 hasConceptScore W4382318911C177769412 @default.
- W4382318911 hasConceptScore W4382318911C184337299 @default.
- W4382318911 hasConceptScore W4382318911C187736073 @default.
- W4382318911 hasConceptScore W4382318911C199360897 @default.
- W4382318911 hasConceptScore W4382318911C199539241 @default.
- W4382318911 hasConceptScore W4382318911C204160518 @default.
- W4382318911 hasConceptScore W4382318911C2776359362 @default.
- W4382318911 hasConceptScore W4382318911C2780451532 @default.
- W4382318911 hasConceptScore W4382318911C33923547 @default.
- W4382318911 hasConceptScore W4382318911C41008148 @default.
- W4382318911 hasConceptScore W4382318911C50644808 @default.
- W4382318911 hasConceptScore W4382318911C94625758 @default.
- W4382318911 hasIssue "10" @default.
- W4382318911 hasLocation W43823189111 @default.
- W4382318911 hasOpenAccess W4382318911 @default.
- W4382318911 hasPrimaryLocation W43823189111 @default.
- W4382318911 hasRelatedWork W2112769827 @default.
- W4382318911 hasRelatedWork W2885094885 @default.
- W4382318911 hasRelatedWork W2961085424 @default.
- W4382318911 hasRelatedWork W4286629047 @default.
- W4382318911 hasRelatedWork W4306674287 @default.
- W4382318911 hasRelatedWork W4316363177 @default.
- W4382318911 hasRelatedWork W4382318911 @default.
- W4382318911 hasRelatedWork W569942085 @default.
- W4382318911 hasRelatedWork W1629725936 @default.
- W4382318911 hasRelatedWork W4224009465 @default.
- W4382318911 hasVolume "37" @default.
- W4382318911 isParatext "false" @default.
- W4382318911 isRetracted "false" @default.
- W4382318911 workType "article" @default.