Implementing Semantic Networks in Parallel Hardware

55 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.

How to Represent Part-Whole Hierarchies in a Neural Network (2021, background): “The components of a vector that are common to birds will learn weights that capture the knowledge that birds ﬂy and the more speciﬁc components that diﬀerentiate penguins from other birds will learn stronger weights that overrule the general case [Hinton, 1981b].”
Extending Machine Language Models toward Human-Level Language Understanding (2019, background): “In general, context-sensitivity is best captured by a mediating representation rather than direct associations among constituents (48).”
The Sparseness of Mixed Selectivity Neurons Controls the Generalization-Discrimination Trade-Off (2013, background): “Indeed, in our case the points live in a low dimensional space (i.e., a space that has a dimensionality that is smaller than the minimum between Nt and p), and this can greatly limit the classification performance (Hinton, 1981; Barak and Rigotti, 2011).”