RESOLVE combines vector symbolic computing with an attention mechanism to improve few-shot accuracy on relational reasoning tasks such as sorting and math problem solving.
We use a batch size of 128 and train for 500 epochs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RESOLVE: Relational Reasoning with Symbolic and Object-Level Features Using Vector Symbolic Processing
RESOLVE combines vector symbolic computing with an attention mechanism to improve few-shot accuracy on relational reasoning tasks such as sorting and math problem solving.