Human unsupervised and supervised learning as a quantitative distinction

Gureckis, T. M., & Love, B. C. (2003a). Human unsupervised and supervised learning as a quantitative distinction. International Journal of Pattern Recognition and Artificial Intelligence, 17(05), 885–901.


Abstract

SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a network model of human category learning. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes/attractors/rules. SUSTAIN has expanded the scope of findings that models of human category learning can address. This paper extends SUSTAIN to account for both supervised and unsupervised learning data through a common mechanism. The modified model, uSUSTAIN (unified SUSTAIN), is successfully applied to human learning data drawn from Love (2002) that compares unsupervised and supervised learning performance.


Bibtex entry:

@article{gureckis2003human,
	abstract = {SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a network model of human category learning. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes/attractors/rules. SUSTAIN has expanded the scope of findings that models of human category learning can address. This paper extends SUSTAIN to account for both supervised and unsupervised learning data through a common mechanism. The modified model, uSUSTAIN (unified SUSTAIN), is successfully applied to human learning data drawn from Love (2002) that compares unsupervised and supervised learning performance.},
	author = {Gureckis, T.M. and Love, B.C.},
	journal = {International Journal of Pattern Recognition and Artificial Intelligence},
	number = {05},
	pages = {885--901},
	publisher = {World Scientific Publishing Company},
	title = {Human unsupervised and supervised learning as a quantitative distinction},
	volume = {17},
	year = {2003}}


QR Code:


Download SVG