Fast relational learning using bottom clause propositionalization with artificial neural networks

By Manoel Vitor Macedo França, Gerson Zaverucha, A.S. d'Avila Garcez. 2013

138 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, methodology): “Also, it is evident that using symbolic knowledge can help improve the efficiency of neural network learning [7, 15].”
End-to-end Differentiable Proving (2017, background): “Other neural-symbolic approaches focus on ﬁrst-order inference, but do not learn subsymbolic vector representations from training facts in a KB ( e.g. , SHRUTI [39], Neural Prolog [40], CLIP++ [41], Lifted Relational Neural Networks [42], and TensorLog [43]).”
Tensor Networks : Deep Learning and Logical Reasoning from Data and Knowledge ⋆ (2016, background): “Finally, related work in the domain of neural-symbolic comp uting and neural network fibring [10] has sought to combine neural networks with I LP to gain efficiency [14] and other forms of knowledge representation, such as pr opositional modal logic and logic programming.”
A historical perspective of explainable Artificial Intelligence (2020, background): “Inductive Logic Programming (ILP), for example, develops a logic program directly from examples (França, Zaverucha, & Garcez, 2014).”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “The former include neural-symbolic systems, which use rules as the basis for the model structure [22], [59], [60], [61].”
Logic Tensor Networks (2020, methodology): “Modify the predictions of a neural network using logical knowledge [46, 14] Encode the satisfiability of logical knowledge in the loss function: LTN and [22, 48] Use of logical knowledge in addition to neural predictions [42, 13] Logical specification of neural networks [26, 68, 23, 58]”
Neurosymbolic AI: the 3rd wave (2020, background): “Foundational work on neural-symbolic integration and neurosymbolic AI models and systems (d’Avila Garcez et al. 2002, 2009; d’Avila Garcez and Lamb 2003; Hammer and Hit-zler 2007), discussed next, will be relevant as we embark in the journey to seek to answer the above research question.”
RelNN: A Deep Neural Model for Relational Learning (2017, background): “The works in (Garcez, Broda, and Gabbay 2012; Franc¸a, Zaverucha, and Garcez 2014; Seraﬁni and Garcez 2016), for instance, proposition-alize the data and miss the chance to learn speciﬁcally about objects.”
Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures (2018, methodology): “…been several works that combine propositional or ﬁrst-order logic with neural networks (Towell, Shavlik, & Noordewier, 1990; Botta et al., 1997; Franca et al., 2014), to the best of our knowledge, none of these existing methods is able to learn weights of latent non-ground relational…”
Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies (2021, background): “França et al. (2014) translated and encoded symbolic knowledge into network weights.”