Rule Induction through Integrated Symbolic and Subsymbolic Processing

How researchers see this paper

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

On the Binding Problem in Artificial Neural Networks (2020, background): “…inductive biases in neural networks that enable them to efficiently learn about symbols and the processes for manipulating them (examples of such an approach are abound, even in early connectionist research, e.g. Smolensky (1990); Pollack (1990); McMillan et al. (1992); Das and Mozer (1993)).”
Computational intelligence methods for rule-based data understanding (2004, methodology): “The search process is further simplified if the prototype weight templates (corresponding to symbolic rules) are used for comparison with the weight vectors [77]—weights are”
Combining Symbolic and Neural Learning (1994, background): “Berenji (1991) and Masuoka et al.(1990) map fuzzy-logic rules, while McMillan, Mozer, and Smolensky (1992) use gating networks (Jacobs et al., 1991) to map production rules.”
Extracting rules from multilayer perceptrons in classification problems: A clustering-based approach (2006, background): “[43] described a neural network called RuleNet, which learns symbolic rules in array manipulation domains.”