Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks

138 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.

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, methodology): “Recent work on conﬁdence rules [51] proposes an eﬃcient method to represent propositional formulas in restricted Boltzmann machines and deep belief networks where inference and learning become easier.”
Logical Rule Induction and Theory Learning Using Neural Theorem Proving (2018, background): “(Tran and D’Avila Garcez 2016) studies the incorporation and extraction of knowledge into deep networks.”
Neurosymbolic AI: the 3rd wave (2020, unknown): “Reasoning about what has been learned allows for extrapolation beyond the data distribution, and finally the symbolic description can serve as prior knowledge (as a constraint) for further learning in the presence of more data, which includes the case of knowledge-based transfer learning [90].”