Corpus ID: 222177093

Abductive Knowledge Induction From Raw Data

  title={Abductive Knowledge Induction From Raw Data},
  author={Wang-Zhou Dai and S. Muggleton},
  • Wang-Zhou Dai, S. Muggleton
  • Published 2020
  • Computer Science
  • ArXiv
  • For many reasoning-heavy tasks, it is challenging to find an appropriate end-to-end differentiable approximation to domain-specific inference mechanisms. Neural-Symbolic (NeSy) AI divides the end-to-end pipeline into neural perception and symbolic reasoning, which can directly exploit general domain knowledge such as algorithms and logic rules. However, it suffers from the exponential computational complexity caused by the interface between the two components, where the neural model lacks… CONTINUE READING
    1 Citations

    Figures and Tables from this paper.


    Bridging Machine Learning and Logical Reasoning by Abductive Learning
    • 11
    • PDF
    Differentiable Reasoning over a Virtual Knowledge Base
    • 17
    • PDF
    Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
    • 38
    • Highly Influential
    • PDF
    Abductive learning: towards bridging machine learning and logical reasoning
    • Z. Zhou
    • Computer Science
    • Science China Information Sciences
    • 2018
    • 32
    • PDF
    Meta-interpretive learning: application to grammatical inference
    • 93
    • Highly Influential
    • PDF
    SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver
    • 44
    • PDF
    Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
    • 1
    • Highly Influential
    • PDF
    Learning Explanatory Rules from Noisy Data
    • 151
    • PDF
    DeepProbLog: Neural Probabilistic Logic Programming
    • 100
    • PDF
    Answer Set Programming
    • 178