Reasoning, Nonmonotonicity and Learning in Connectionist Networks that Capture Propositional Knowledge

How researchers see this paper

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

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, background): “Penalty logic shows an equivalence between minimising violation and minimising energy functions of symmetric connectionist networks [35].”
Neurosymbolic AI: the 3rd wave (2020, unknown): “However, the value of distributed approximate reasoning using neural networks is only starting to be investigated as in the case of differentiable neural computers [33] and neural theorem proving [97], although early efforts did not prove to be promising in terms of practical efficiency [62, 38, 82]”
Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks (2018, unknown): “The idea of representing each formula into a clique of Markov network is similar to that of penalty logic, which has been proposed to integrate symbolic knowledge and Hopﬁeld networks [32].”
Neural-Symbolic Learning and Reasoning: A Survey and Interpretation (2017, methodology): “In fact, in (Pinkas, 1995) equivalence has been shown between minimising the energy of symmetric ANNs and satisfiability of penalty logic, i.”
The Connectionist Inductive Learning and Logic Programming System (1999, background): “Pinkas [7, 8] and Holldobler [9] have made important contributions to the subject of neural-symbolic integration, showing the capabilities and limitations of neural networks for performing logical inference.”