Knowledge Extraction from Deep Belief Networks for Images

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): “In [50, 51], it has been shown that while extracting conjunctive clauses from the ﬁrst layer of a deep belief network is fast and eﬀective, extraction in higher layers results in a loss of accuracy.”
Characterization of Symbolic Rules Embedded in Deep DIMLP Networks: A Challenge to Transparency of Deep Learning (2017, methodology): “The ﬁrst work on rule inference from Deep Belief Networks was achieved by Garcez and Tran [16].”
Neural-Symbolic Learning and Reasoning: Contributions and Challenges (2015, background): “There is also a very well developed logical theory of action, for instance related to the basic propositional logic of programs PDL (Harel, Kozen, and Tiuryn, 2001), capturing what holds true after various combinations of actions.”
Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks (2018, unknown): “A simple symbolic language for hierarchical knowledge representation, named conﬁdence rules [17]–[19], is deployed and evaluated.”
Non-iterative Knowledge Fusion in Deep Convolutional Neural Networks (2018, background): “Tran and Garcez [30, 31] demonstrated that a set of logical rules, called conﬁdence rules, can be extracted and inserted into restricted Boltzmann machines and deep belief networks.”