Learning features while learning to classify: a cognitive model for autonomous systems
Michael Martin (),
Christian Lebiere (),
MaryAnne Fields () and
Craig Lennon ()
Additional contact information
Michael Martin: Carnegie Mellon University
Christian Lebiere: Carnegie Mellon University
MaryAnne Fields: Army Research Laboratory
Craig Lennon: Army Research Laboratory
Computational and Mathematical Organization Theory, 2020, vol. 26, issue 1, No 2, 23-54
Abstract:
Abstract We describe a computational cognitive model intended to be a generalizable classifier that can provide context-based feedback to semantic perception in robotic applications. Many classifiers (including cognitive models of categorization) perform well at the task of associating features with objects. Underlying their performance is an effective selection of the features used during classification. This feature selection (FS) process is usually performed outside the boundaries of the models that learn and perform classification tasks, often by human experts. In contrast, the cognitive model we describe simultaneously learns which features to use, as it learns the associations between features and classes. This integration of FS and class learning in one model makes it complementary to other machine-learning techniques that generate feature-based representations (e.g., deep learning methods). But their integration in a cognitive architecture also provides a means for creating a dynamic context that includes disparate sources of information (e.g., environmental observations, task knowledge, commands from humans). This richer context, in turn, provides a means for making semantic perception goal-directed. We demonstrate automated FS, integrated with an instance-based learning approach to classification, in an ACT-R model of categorization by labeling facial expressions of emotion (e.g., happy, sad), and then generalizing the model to the classification of indoor public spaces (e.g., cafes, classrooms).
Keywords: Autonomous systems; Feature selection; Cognitive architectures; Machine-learning; Classification; Instance-based learning (search for similar items in EconPapers)
Date: 2020
References: View complete reference list from CitEc
Citations:
Downloads: (external link)
http://link.springer.com/10.1007/s10588-018-9279-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:spr:comaot:v:26:y:2020:i:1:d:10.1007_s10588-018-9279-3
Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10588
DOI: 10.1007/s10588-018-9279-3
Access Statistics for this article
Computational and Mathematical Organization Theory is currently edited by Terrill Frantz and Kathleen Carley
More articles in Computational and Mathematical Organization Theory from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().