How Do Simple Connectionist Networks Achieve a Shift From "Featural" to "Correlational" Processing in Categorization? Export

@article{citeulike:540518, abstract = {Three developmental connectionist models simulate a purported shift from "featural" to "correlational" processing in infant categorization (models: Gureckis \& Love, 2004/this issue; Shultz \& Cohen, 2004/this issue; Westermann \& Mareschal, 2004/this issue; empirical data: Cohen \& Arthur, 2003; Younger, 1985; Younger \& Cohen, 1986). In this article, the way in which the models are able to simulate the behavioral data is revealed, and their respective theoretical commitments are evaluated. Together the models argue that the shift from featural to correlational processing in infant categorization might be illusory, as these models are able to replicate the key behavioral features while processing correlations right from the start. As such, they claim the behavioral description of a shift is not reflected at the level of mechanism.}, author = {Thomas, Michael S. C.}, citeulike-article-id = {540518}, journal = {Infancy}, keywords = {4, categorization, model\_comparison, neural\_network, progressive\_development}, number = {2}, pages = {199--208}, posted-at = {2006-03-08 18:25:47}, priority = {4}, title = {How Do Simple Connectionist Networks Achieve a Shift From "Featural" to "Correlational" Processing in Categorization?}, volume = {5}, year = {2004} }

TY - JOUR ID - citeulike:540518 L3 - citeulike-article-id:540518 N2 - Three developmental connectionist models simulate a purported shift from "featural" to "correlational" processing in infant categorization (models: Gureckis & Love, 2004/this issue; Shultz & Cohen, 2004/this issue; Westermann & Mareschal, 2004/this issue; empirical data: Cohen & Arthur, 2003; Younger, 1985; Younger & Cohen, 1986). In this article, the way in which the models are able to simulate the behavioral data is revealed, and their respective theoretical commitments are evaluated. Together the models argue that the shift from featural to correlational processing in infant categorization might be illusory, as these models are able to replicate the key behavioral features while processing correlations right from the start. As such, they claim the behavioral description of a shift is not reflected at the level of mechanism. IS - 2 JF - Infancy EP - 208 TI - How Do Simple Connectionist Networks Achieve a Shift From "Featural" to "Correlational" Processing in Categorization? VL - 5 SP - 199 KW - 4 KW - categorization KW - model_comparison KW - neural_network KW - progressive_development AU - Thomas, Michael PY - 2004/// ER -