In M. Fulk and J. Case, eds., ACM 3rd Annual Workshop on Computational Learning Theory, Morgan Kaufmann, San Francisco, CA. V. Fedorov. (1972) Theory of Optimal Experiments.  Home/Search   Document Not in Database   Summary   Related Articles

....least 50 years. We will just mention here a few closely related theoretical results and empirical studies; the interested reader should consult Atkinson and Donev [1992] for a survey of results and applications using optimal experiment design. A canonical description of the theory of OED is given in Fedorov [1972]. MacKay [1992] showed that OED could be incorporated into a Bayesian framework for neural network data selection and described several interesting optimization criteria. Sollich [1994] considers the theoretical generalization performance of linear networks given greedy vs. globally optimal ....

....design applied to neural network learning. As stated in the introduction, our primary goal is to minimize EMSE . An alternative goal of system identification is discussed briefly in the appendix, and other interesting goals, such as eigenvalue maximization and entropy minimization, may be found in Fedorov [1972] and MacKay [1992] Error minimization is pursued in the OED framework by selecting data to minimize model uncertainty. Uncertainty in this case is manifested as the learner s estimated output variance oe 2 y . The justification for selecting data to minimize variance comes from the nature of ....

In M. Fulk and J. Case, eds., ACM 3rd Annual Workshop on Computational Learning Theory, Morgan Kaufmann, San Francisco, CA. V. Fedorov. (1972) Theory of Optimal Experiments.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC