Neural-symbolic learning systems - foundations and applications

By A.S. d'Avila Garcez, K. Broda, Dov M. Gabbay. 2012

339 citations recorded by the source corpus.

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

Citations in the corpus

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, methodology): “Inspired by this work, in [15], the CILP++ system is proposed by integrating bottom clauses and rule-based approach CILP [17], referred to in Section 3.”
Integrating Learning and Reasoning with Deep Logic Models (2019, background): “The integration of learning from data and symbolic reasoning [10] has recently attracted a lot of attention.”
DeepProbLog: Neural Probabilistic Logic Programming (2018, methodology): “Recently, a number of researchers have revisited and modernized older ideas originating from the ﬁeld of neural-symbolic integration [Garcez et al., 2012], searching for ways to combine the best of both worlds [Boˇsnjak et al., 2017, Rockt¨aschel and Riedel, 2017, Cohen et al., 2018, Santoro et…”
End-to-end Differentiable Proving (2017, background): “Combining neural and symbolic approaches to relational learning and reasoning has a long tradition and let to various proposed architectures over the past decades (see [38] for a review).”
Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning (2017, neutral): “These neural-symbolic systems (Garcez et al., 2012) include early examples such as KBANN (Towell et al.”
Towards Neural Theorem Proving at Scale (2018, background): “Recent advancements in deep learning intensified the longstanding interests in integrating symbolic reasoning with connectionist models (Shen, 1988; Ding et al., 1996; Garcez et al., 2012; Marcus, 2018).”
Attention in Natural Language Processing (2019, background): “Popular approaches include statistical relational learning [147], neural-symbolic learning [148], and the application of various deep learning architectures [149], such as memory networks [59], neural Turing machines [142], and several others.”
Explainable Deep Learning: A Field Guide for the Uninitiated (2020, background): “Semantically interpretable descriptions are rooted in the field of neuro-symbolic computing (Garcez et al., 2012).”
Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures (2018, methodology): “Our approach is also generally related to prior art in combining logical rules with neural networks, also known as neural-symbolic integration (d’Avila Garcez, Broda, & Gabbay, 2012), such as in the KBANN system (Towell et al., 1990).”
Learning Knowledge Base Inference with Neural Theorem Provers (2016, background): “Combining neural and symbolic approaches for relational learning and reasoning has let to many promising neural network architectures over the past decades (Garcez et al., 2012).”
Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, background): “…problem of combining symbolism and connectionism has been researched since the 1980s (Gallant, 1988, 1993; Shavlik et al., 1991; Towell and Shavlik, 1994a, 1994b), and has drawn much attention recent years (Besold et al., 2017; de Penning et al., 2011; Garcez et al., 2012, 2019; Lamb et al., 2020).”
Book Reviews: The Proper Treatment of Events, by Michiel van Lambalgen and Fritz Hamm (2005, methodology): “For more information on this, we refer the reader to Stenning and van Lambalgen [94], [96] and d’Avila Garcez, Broda and Gabbay [23].”
Neural-Symbolic Learning and Reasoning: A Survey and Interpretation (2017, methodology): “Most recently, NSCA has been included in an Intelligent Transport System to reduce CO2 emissions (de Penning, d’Avila Garcez, Lamb, Stuiver, & Meyer, 2014).”
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.”