Selective Sampling Using the Query by Committee Algorithm |
| |
Authors: | Freund Yoav Seung H Sebastian Shamir Eli Tishby Naftali |
| |
Affiliation: | (1) AT&T Labs, Florham Park, NJ, 07932;(2) Bell Laboratories, Lucent Technologies, Murray Hill, NJ, 07974;(3) Institute of Computer Science, Hebrew University, Jerusalem, ISRAEL |
| |
Abstract: | 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 perceptrons. |
| |
Keywords: | selective sampling query learning Bayesian Learning experimental design |
本文献已被 SpringerLink 等数据库收录! |
|