TY - GEN
T1 - Information, prediction, and query by committee
AU - Freund, Yoav
AU - Seung, H. Sebastian
AU - Shamir, Eli
AU - Tishby, Naftali
N1 - Publisher Copyright:
© 1992 Neural information processing systems foundation. All rights reserved.
PY - 1992
Y1 - 1992
N2 - We analyze the "query by committee" algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of thresholded smooth functions.
AB - We analyze the "query by committee" algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of thresholded smooth functions.
UR - https://www.scopus.com/pages/publications/105021002031
UR - https://www.scopus.com/pages/publications/105021002031#tab=citedBy
U2 - 10.5555/2987061.2987121
DO - 10.5555/2987061.2987121
M3 - Conference contribution
AN - SCOPUS:105021002031
T3 - Advances in Neural Information Processing Systems
SP - 483
EP - 490
BT - Advances in Neural Information Processing Systems 5, NIPS 1992
A2 - Hanson, Stephen Jose
A2 - Cowan, Jack D.
A2 - Giles, C. Lee
PB - Neural information processing systems foundation
T2 - 5th Advances in Neural Information Processing Systems, NIPS 1992
Y2 - 30 November 1992 through 3 December 1992
ER -