Modular design patterns for neural-symbolic integration: refinement and combination
Not on the map. Why?
Abstract (arXiv)
We formalise some aspects of the neural-symbol design patterns of van Bekkum et al., such that we can formally define notions of refinement of patterns, as well as modular combination of larger patterns from smaller building blocks. These formal notions are being implemented in the heterogeneous tool set (Hets), such that patterns and refinements can be checked for well-formedness, and combinations can be computed.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 8 of its 19 references that are in the map. First posted on arXiv 9 Jun 2022.
Builds on
8 of 19 references.
References · 8
- 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 203
- 2020Logic Tensor Networkscited by 197
- 2020Logical Neural Networkscited by 118
- 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
- 2020OWL2Vec*: Embedding of OWL Ontologiescited by 63
- 2021Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use casescited by 39
- 2022Neuro-Symbolic Verification of Deep Neural Networkscited by 21
- 2021Modular Design Patterns for Hybrid Actorscited by 2
Built on by
Citing papers per year: 2024: 1.
1 paper.