SCAN: A Scalable Model of Attentional Selection

E.O. Postma*, H.J. van den Herik, P Hudson

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review


This paper describes the SCAN (Signal Channelling Attentional Network) model, a scalable neural network model for attentional scanning. The building block of SCAN is a gating lattice, a sparsely-connected neural network defined as a special case of the Ising lattice from statistical mechanics. The process of spatial selection through covert attention is interpreted as a biological solution to the problem of translation-invariant pattern processing. In SCAN, a sequence of pattern translations combines active selection with translation-invariant processing. Selected patterns are channelled through a gating network, formed by a hierarchical fractal structure of gating lattices, and mapped onto an output window. We show how the incorporation of an expectation-generating classifier network (e.g. Carpenter and Grossberg's ART network) into SCAN allows attentional selection to be driven by expectation. Simulation studies show the SCAN model to be capable of attending and identifying object patterns that are part of a realistically sized natural image.
Original languageEnglish
Pages (from-to)993-1015
JournalNeural Networks
Issue number6
Publication statusPublished - 1 Jan 1997


Dive into the research topics of 'SCAN: A Scalable Model of Attentional Selection'. Together they form a unique fingerprint.

Cite this