Learning to reason

By Roni Khardon, Dan Roth. 1994

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, background): “The integration of learning and reasoning through neural-symbolic computing has been an active branch of AI research for several years [14, 16, 17, 21, 25, 42, 53].”
From machine learning to machine reasoning (2011, background): “Although there are connectionist and machine learning approaches to variable binding (e.g., Smolensky 1990; Plate 1994; Khardon and Roth 1997), they cannot avoid the computational complexity of first-order logic problems.”
The locus of the myside bias in written argumentation (2008, background): “In two experiments on informal or everyday reasoning Perkins et al. (1986) found significant positive correlations between general intelligence, as measured by Quick Word scores, and myside arguments, but practically no correlation between general intelligence and the generation of other side…”
Neural-Symbolic Learning and Reasoning: Contributions and Challenges (2015, background): “Consolidation: Learning to Reason (L2R) is a framework that makes learning an integral part of the reasoning process (Khardon and Roth, 1997).”
Neurosymbolic AI: the 3rd wave (2020, unknown): “Neural-symbolic computing has been an active area of research seeking to establish such a bridge for several years [4, 26, 16, 20, 35, 43, 80, 93].”
Blending Learning and Inference in Conditional Random Fields (2016, background): “This concept was put forward in the general framework of learning to reason by Khardon and Roth (1997) and we leave for future research to find different frameworks which have similar learning-prediction robustness.”
Knowledge Infusion (2006, methodology): “Khardon and Roth (1997) offer a theory of “learning to reason,” in which reasoning is made redundant in some such sense.”
Argumentation Schema and the Myside Bias in Written Argumentation (2009, methodology): “…useful in assessing individual differences among people (Macpherson & Stanovich, 2007), shedding light on the effects of education (Toplak & Stanovich, 2003) and determining correlations between measures of intelligence and the proportion of other-side reasons generated (Perkins et al., 1986).”
AI Reasoning Systems: PAC and Applied Methods (2018, methodology): “[12] • Learning many rules over an ontology is not much harder than learning a single rule over the same ontology.”
A Knowledge Compilation Map (2002, unknown): “…the computational intractability of general propositional reasoning (Darwiche, 1999; Cadoli & Donini, 1997; Boufkhad, Grégoire, Marquis, Mazure, & Säıs, 1997; Khardon & Roth, 1997; Selman & Kautz, 1996; Schrag, 1996; Marquis, 1995; del Val, 1994; Dechter & Rish, 1994; Reiter & de Kleer, 1987).”