Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques

Andrea Rafanelli (University of Pisa; Italy; Italy); University of L'Aquila

REVIEW

Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2308.15899 v1 pith:DPRAIM35 submitted 2023-08-30 cs.AI cs.LGcs.LOcs.MA

Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques

Andrea Rafanelli (University of Pisa , Italy , University of L'Aquila , Italy) This is my paper

classification cs.AI cs.LGcs.LOcs.MA

keywords knowledgesymbolicinjectionlearninglogicnetworksneuralpopular

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

Deep Learning (DL) models have become popular for solving complex problems, but they have limitations such as the need for high-quality training data, lack of transparency, and robustness issues. Neuro-Symbolic AI has emerged as a promising approach combining the strengths of neural networks and symbolic reasoning. Symbolic knowledge injection (SKI) techniques are a popular method to incorporate symbolic knowledge into sub-symbolic systems. This work proposes solutions to improve the knowledge injection process and integrate elements of ML and logic into multi-agent systems (MAS).

Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques

discussion (0)