Does Cognitive Science Need Kernels? Export

@article{citeulike:5722951, abstract = {Kernel methods are among the most successful tools in machine learning and are used in challenging data analysis problems in many disciplines. Here we provide examples where kernel methods have proven to be powerful tools for analyzing behavioral data, especially for identifying features in categorization experiments. We also demonstrate that kernel methods relate to perceptrons and exemplar models of categorization. Hence, we argue that kernel methods have neural and psychological plausibility, and theoretical results concerning their behavior are therefore potentially relevant for human category learning. In particular, we believe kernel methods have the potential to provide explanations ranging from the implementational via the algorithmic to the computational level.}, author = {J\"{a}kel, Frank and Sch\"{o}lkopf, Bernhard and Wichmann, Felix A.}, citeulike-article-id = {5722951}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.tics.2009.06.002}, citeulike-linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S1364661309001430}, day = {02}, doi = {10.1016/j.tics.2009.06.002}, issn = {13646613}, journal = {Trends in Cognitive Sciences}, keywords = {computation, learning, psychology, review, theory}, month = {September}, number = {9}, pages = {381--388}, posted-at = {2009-09-13 03:07:00}, priority = {1}, title = {Does Cognitive Science Need Kernels?}, url = {http://dx.doi.org/10.1016/j.tics.2009.06.002}, volume = {13}, year = {2009} }

TY - JOUR ID - citeulike:5722951 L3 - citeulike-article-id:5722951 N2 - Kernel methods are among the most successful tools in machine learning and are used in challenging data analysis problems in many disciplines. Here we provide examples where kernel methods have proven to be powerful tools for analyzing behavioral data, especially for identifying features in categorization experiments. We also demonstrate that kernel methods relate to perceptrons and exemplar models of categorization. Hence, we argue that kernel methods have neural and psychological plausibility, and theoretical results concerning their behavior are therefore potentially relevant for human category learning. In particular, we believe kernel methods have the potential to provide explanations ranging from the implementational via the algorithmic to the computational level. IS - 9 JF - Trends in Cognitive Sciences SN - 13646613 EP - 388 TI - Does Cognitive Science Need Kernels? VL - 13 SP - 381 KW - computation KW - learning KW - psychology KW - review KW - theory AU - Jäkel, Frank AU - Schölkopf, Bernhard AU - Wichmann, Felix PY - 2009/09/02/ UR - http://dx.doi.org/10.1016/j.tics.2009.06.002 ER -