Neural-Symbolic Cognitive Reasoning

By A.S. d'Avila Garcez, L. C. Lamb, Dov M. Gabbay. 2008

232 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Prompting & Reasoning, Knowledge Graphs & Representation

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 Cognitive Neuroscience

In Prompting & Reasoning

In Knowledge Graphs & Representation

Citations in the corpus

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, methodology): “Neural-symbolic systems have been applied successfully to several fields, including data science, ontology learning, training and assessment in simulators, and models of cognitive learning and reasoning [5, 14, 16, 34].”
Learning Explanatory Rules from Noisy Data (2017, background): “More recently, nonclassical logics such as modal logics, nonmonotonic propositional logics, and argumentation frameworks have been encoded in neural nets (Garcez, Gabbay, Ray, & Woods, 2007; Garcez et al., 2008; Garcez, Lamb, & Gabbay, 2009; Garcez, Gabbay, & Lamb, 2014).”
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).”
Neurosymbolic AI: the 3rd wave (2020, background): “Neu-rosymbolic AI has shown that non-classical logics, in particular many-valued logics, offer an adequate language for describing neural networks (d’Avila Garcez et al. 2009; Serafini and d’Avila Garcez 2016; Riegel et al. 2020).”
Emerging Technology and Business Model Innovation: The Case of Artificial Intelligence (2019, background): “It assumes that high-level representation of knowledge (symbol) and combinations of symbols can achieve human-like AI by performing reasoning in a manner similar to how humans express their thoughts and draw conclusions from deductive reasoning [16].”
Reasoning in Non-probabilistic Uncertainty: Logic Programming and Neural-Symbolic Computing as Examples (2017, background): “Yet, within the area of neural-symbolic computing [15], equivalences have been proved between LP and neural networks, which indicate the possibility of reconciling such apparently very distinct representational frameworks.”
Neural Logic Networks (2019, background): “[4]’s framework has been verified helpful in nonclassical logic, abductive reasoning, and normative multi-agent systems, these frameworks focus more on hard logic reasoning and are short of learning representations and generalization ability compared with deep neural networks, and thus are not suita”
Learning and reasoning in logic tensor networks: theory and application to semantic image interpretation (2017, background): “Finally, related work in the domain of neural-symbolic computing and neural network fibring [4] has sought to com-”
Fast relational learning using bottom clause propositionalization with artificial neural networks (2013, unknown): “In neural-symbolic integration, the representation of first-order logic by neural networks is of interest in its own right, since first-order logic learning and reasoning using connectionist systems remains an open research question (Garcez et al., 2008).”
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.”
Neural-Symbolic Learning and Reasoning: A Survey and Interpretation (2017, methodology): “Also within a more practical approach, an extension of the above fixed-point method to multiple networks, as shown in Figure 1, has been proposed in (Garcez et al., 2009).”
Logic Tensor Networks (2020, background): “Early work in this direction has shown correspondences between various logical-symbolic systems and neural network models [27, 64, 66, 32, 53].”
Neural-Symbolic Learning and Reasoning: Contributions and Challenges (2015, background): “There has been much successful work in the neuralsymbolic computation community on extracting logical expressions from trained neural networks, and using this extracted knowledge to seed learning in further tasks (see d'Avila Garcez, Lamb, and Gabbay (2009) for an overview).”