Abstract | ||
---|---|---|
We present a new method for obtaining local error bars for nonlinear regression, i.e., estimates of the confidence in predicted values that de- pend on the input. We approach this problem by applying a maximum- likelihood framework to an assumed distribution of errors. We demon- strate our method first on computer-generated data with locally varying, normally distributed target noise. We then apply it to laser data from the Santa Fe Time Series Competitionwhere the underlying system noise is known quantization error and the error bars give local estim ates of model misspecification. In both cases, the method also provides a weighted- regression effect that improves generalization performan ce. |
Year | Venue | Keywords |
---|---|---|
1994 | NIPS | quantization error,maximum likelihood,normal distribution,time series,nonlinear regression |
Field | DocType | Citations |
Unit-weighted regression,Nonlinear regression,Artificial intelligence,Error bar,Quantization (signal processing),Machine learning,Mathematics | Conference | 28 |
PageRank | References | Authors |
6.52 | 1 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
David A. Nix | 1 | 101 | 14.52 |
Andreas S. Weigend | 2 | 576 | 112.30 |