KSL-98-04 + redirect page
Learning of Compositional Hierarchies for the modeling of context effects + Has identifier
Learning of Compositional Hierarchies for the modeling of context effects + Ksl tr id
Learning of Compositional Hierarchies for the modeling of context effects + Number
| Learning of Compositional Hierarchies for the modeling of context effects |
Bibtype
techreport
Has publishing details
January,1998
Has title
Learning of Compositional Hierarchies for the modeling of context effects
Has where published
KSL-98-04
Has year
1998
Title
Learning of Compositional Hierarchies for the modeling of context effects
Year
1998
Abstract
Compositional, or part-whole, hierarchies … Compositional, or part-whole, hierarchies underlie many forms of data, and representations involving these structures lie at the heart of much of the work in Artificial Intelligence and Cognitive Science. However, despite their prevalence, general methods for learning such structures from data are scarce. This paper presents a learning and prediction system that learns compositional hierarchies and uses them to mediate context effects in making predictions. The model is a hybrid system based on an early psychological neural network system, the Interactive Activation model of context effects in letter perception, and an elegant new symbolic hierarchy-generation algorithm called Sequitur. The composite system overcomes an important limitation in each of its parents. portant limitation in each of its parents.
Author
Karl Pfleger and Barbara Hayes-Roth +
Has author
Karl Pfleger and Barbara Hayes-Roth +
Has identifier
Learning of Compositional Hierarchies for the modeling of context effects +
Institution
Knowledge Systems, AI Laboratory +
Ksl tr id
Learning of Compositional Hierarchies for the modeling of context effects +
Month
January +
Number
Learning of Compositional Hierarchies for the modeling of context effects +
Process note
NO +
Categories KSL Technical Report +, Publication +, Technical Report +
|
