The Connectionist Inductive Learning and Logic Programming System

By A.S. d'Avila Garcez, Gerson Zaverucha. 1999

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

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, methodology): “an ANN can be constructed as in Figure 2a. CILP then generalises the idea by using recurrent networks and bounded continuous units [7].”
End-to-end Differentiable Proving (2017, neutral): “, EBL-ANN [39], KBANN [40] and C-IL(2)P [41]).”
Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks (2018, unknown): “The idea of encoding knowledge into DBNs to improve learning performance is inspired by early work on knowledge-based neural networks [34], [35].”
Neural Logic Networks (2019, background): “Researchers further developed logical programming systems to make logical inference [5, 11], and proposed neural knowledge representation and reasoning frameworks [2, 1] for logical reasoning.”
A Connectionist Computational Model for Epistemic and Temporal Reasoning (2006, methodology): “The CTLK uses ensembles of connectionist inductive learning and logic programming (C-ILP) neural networks (d’Avila Garcez, Broda, et al., 2002; d’Avila Garcez & Zaverucha, 1999).”
Learning Knowledge Base Inference with Neural Theorem Provers (2016, background): “Early proposals for neural-symbolic networks are limited to propositional formulae ( e.g. , EBL-ANN (Shavlik and Tow-ell, 1989), KBANN (Towell and Shavlik, 1994) and C-ILP (Garcez and Zaverucha, 1999)).”
Neurosymbolic AI: the 3rd wave (2020, background): “…representation, within neurosymbolic AI one may identify systems that translate and encode symbolic knowledge into the set of weights of a network (d’Avila Garcez and Zaverucha 1999; d’Avila Garcez et al. 2002, 2009; Ham-mer and Hitzler 2007; Hu et al. 2016) and systems that translate and encode…”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “Extensions are available that also output a revised rule set [54] or also consider first-order”
Explaining Trained Neural Networks with Semantic Web Technologies: First Steps (2017, unknown): “, [2,9,16]), which pursued very similar goals.”
Dimensions of Neural-symbolic Integration - A Structured Survey (2005, methodology): “As [Hölldobler and Kalinke, 1994] employed binary threshold units as activation functions of the network nodes, the results were lifted to sigmoidal and hence differentiable activation func- tions in [Garcez et al., 1997, Garcez and Zaverucha, 1999].”
Propositional Knowledge Representation and Reasoning in Restricted Boltzmann Machines. (2017, methodology): “Practically, this would help neural-symbolic integration models perform better (Towell and Shavlik 1994; Avila Garcez and Zaverucha 1999).”
Neural-Symbolic Learning and Reasoning: A Survey and Interpretation (2017, methodology): “(ii) Central Executive Function: The notion of a centralised control system that guides thought (a Central Executive) is common in information processing theories of cognition, c.f. Baddeley and Hitch’s working memory model (Baddeley, 2000), Shallice’s Supervisory Attentional System (Norman & Shalli”
Embedding Logic Rules Into Recurrent Neural Networks (2019, background): “ENL-ANN [20], KBANN [21], and C-ILP [22], which are limited to propositional formulae, suggest that combing given rules with neural network structures lead to explanatory and knowledge acquisition.”
Fast relational learning using bottom clause propositionalization with artificial neural networks (2013, unknown): “Keywords: Relational Learning, Inductive Logic Programming, Propositionalization, Neural-Symbolic Integration, Artificial Neural Networks”