Learning from a population of hypotheses

@article{citeulike:2070618, abstract = {We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approximate an unknown target function arbitrarily well. Our motivation includes the question of how to make optimal use of multiple independent runs of a mediocre learning algorithm, as well as settings in which the many hypotheses are obtained by a distributed population of identical learning agents.}, author = {Kearns, Michael and Seung, Sebastian H. }, citeulike-article-id = {2070618}, journal = {Machine Learning}, keywords = {learning\_algori}, month = {February}, number = {2}, pages = {255--276}, posted-at = {2007-12-07 02:56:29}, priority = {2}, title = {Learning from a population of hypotheses}, url = {http://dx.doi.org/10.1007/BF00993412}, volume = {18}, year = {1995} }

TY - JOUR ID - citeulike:2070618 L3 - citeulike-article-id:2070618 TI - Learning from a population of hypotheses JF - Machine Learning VL - 18 IS - 2 SP - 255 EP - 276 N2 - We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approximate an unknown target function arbitrarily well. Our motivation includes the question of how to make optimal use of multiple independent runs of a mediocre learning algorithm, as well as settings in which the many hypotheses are obtained by a distributed population of identical learning agents. KW - learning_algori AU - Kearns, Michael AU - Seung, Sebastian PY - 1995/02/01/ UR - http://dx.doi.org/10.1007/BF00993412 ER -