Acquiring Contextualized Concepts: A Connectionist Approach
Article first published online: 4 MAY 2011
Copyright © 2011 Cognitive Science Society, Inc.
Volume 35, Issue 6, pages 1162–1189, August 2011
How to Cite
van Dantzig, S., Raffone, A. and Hommel, B. (2011), Acquiring Contextualized Concepts: A Connectionist Approach. Cognitive Science, 35: 1162–1189. doi: 10.1111/j.1551-6709.2011.01178.x
- Issue published online: 26 JUL 2011
- Article first published online: 4 MAY 2011
- Received 23 November 2009; received in revised form 8 November 2010; accepted 10 November 2010
- Concept learning;
- Top-down context influence;
- Hierarchical categorization;
- Neural network
Conceptual knowledge is acquired through recurrent experiences, by extracting statistical regularities at different levels of granularity. At a fine level, patterns of feature co-occurrence are categorized into objects. At a coarser level, patterns of concept co-occurrence are categorized into contexts. We present and test CONCAT, a connectionist model that simultaneously learns to categorize objects and contexts. The model contains two hierarchically organized CALM modules (Murre, Phaf, & Wolters, 1992). The first module, the Object Module, forms object representations based on co-occurrences between features. These representations are used as input for the second module, the Context Module, which categorizes contexts based on object co-occurrences. Feedback connections from the Context Module to the Object Module send activation from the active context to those objects that frequently occur within this context. We demonstrate that context feedback contributes to the successful categorization of objects, especially when bottom-up feature information is degraded or ambiguous.