3 results for "example domain"
ARXIV.ORG
Constraint-Based Analysis of Reasoning Shortcuts in Neurosymbolic Learning
Neurosymbolic systems can satisfy logical constraints during learning without achieving the intended concept-label correspondence; this is a problem known as reasoning shortcuts. We formalize reasonin…
ARXIV.ORG
Information-Theoretic Measures in AI: A Practical Decision Guide
Information-theoretic (IT) measures are ubiquitous in artificial intelligence: entropy drives decision-tree splits and uncertainty quantification, cross-entropy is the default classification loss, mut…
ARXIV.ORG
NeSyCat: A Monad-Based Categorical Semantics of the Neurosymbolic ULLER Framework
ULLER (Unified Language for LEarning and Reasoning) offers a unified first-order logic (FOL) syntax, enabling its knowledge bases to be used directly across a wide range of neurosymbolic systems. The …