Neural-Symbolic Learning and Reasoning: Contributions and Challenges

By A.S. d'Avila Garcez, Tarek R. Besold, Luc De Raedt, Peter Földiák, Pascal Hitzler, Thomas F. Icard III, Kai-Uwe Kühnberger, L. C. Lamb, Risto Miikkulainen, Daniel L. Silver. 2015

201 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.

Citations in the corpus

What Does Explainable AI Really Mean? A New Conceptualization of Perspectives (2017, methodology): “Eﬀorts in neural-symbolic integration [3] aim to develop methods which might enable explicit automated reasoning over model properties and decision factors by extracting symbolic rules from connectionist models.”
Explainability in Deep Reinforcement Learning (2020, background): “Some work has been done to learn representations by combining symbolic AI with deep RL in order to facilitate the use of background knowledge, the exploitation of learnt knowledge, and to improve generalization [38, 35, 88, 37] Consequently, it also improves the explainability of the algorithms, whi”
Exploring End-to-End Differentiable Natural Logic Modeling (2020, methodology): “…the long-standing problem of bringing together the complementary strengths of neural networks and symbolic models, e.g., the research performed in (Garcez et al., 2015; Yang et al., 2017; Rockt¨aschel and Riedel, 2017; Evans and Grefenstette, 2018; Weber et al., 2019; De Raedt et al., 2019; Mao…”
Conversational Neuro-Symbolic Commonsense Reasoning (2020, background): “Neuro-symbolic systems are hybrid models that leverage the robustness of connectionist methods and the soundness of symbolic reasoning to effectively integrate learning and reasoning [28,29].”
Hybrid Decision Making: When Interpretable Models Collaborate With Black-Box Models (2018, background): “So far these representations have been low level, and have not been integrated with the high-level symbolic representations used in knowledge representation [8].”
Neurosymbolic AI: the 3rd wave (2020, background): “In a neurosymbolic system, it is possible to envisage the combination of efficient approximate reasoning (jumping to conclusions) with more deliberative and precise or normative symbolic reasoning (d’Avila Garcez et al. 2015; Valiant 2003).”
A historical perspective of explainable Artificial Intelligence (2020, background): “, 2019), with applications in recommender systems (Tintarev & Masthof, 2015), and approaches of neural-symbolic learning and reasoning (Garcez et al., 2015).”
Deep learning for noise-tolerant RDFS reasoning (2019, background): “In the semantic matching models, the entities are represented by their latent semantic attributes and their relations “are encoded as bilinear operators on the entities [62, 3]”.”
Explaining Trained Neural Networks with Semantic Web Technologies: First Steps (2017, methodology): “y in our approach. In Section 3 we present the conceptual and experimental setup 1 How to go beyond the propositional paradigm in neural-symbolic integration is one of the major challenges in the eld [8]. Explaining Trained Neural Networks with Semantic Web Technologies 3 for our approach, and repor”
Learning to Solve NP-Complete Problems - A Graph Neural Network for the Decision TSP (2018, background): “However, the application of deep learning to symbolic domains directly, as opposed to their use in reinforcement learning agents, is still incipient (d’Avila Garcez et al. 2009; d’Avila Garcez et al. 2015; Evans and Grefenstette 2018).”
Differentiable Reasoning on Large Knowledge Bases and Natural Language (2019, background): “A promising strategy for overcoming these issues consists of combining neural models and symbolic reasoning , given their complementary strengths and weaknesses (d’Avila Garcez et al. 2015; Rockt ¨ aschel and Riedel 2017; Yang, Yang, and Cohen 2017; Evans and Grefenstette 2018; Weber et al. 2019).”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “On the other hand, another direction is to promote the use of neuro-symbolic learning and reasoning in parallel, each one informing the other at all stages of model construction and evaluation [45].”
Emerging Technology and Business Model Innovation: The Case of Artificial Intelligence (2019, methodology): “proposed a novel method for neural symbolic integration [31], and they verified the feasibility of their proposed method by implementing logic tensor networks [32].”