Improving the Structuring Capabilities of Statistics–Based Local Learners
Function approximation, a mainstay of machine learning, is a useful tool in science and engineering. Local learning approches subdivide the learning space into regions to be approximated locally by linear models. An arrangement of regions that conforms to the structure of the target function leads to learning with fewer resources and gives an insight into the function being approximated. This paper introduces a covariance–based update for the size and shape of each local region. An evaluation shows that the method improves the structuring capabilities of state–of–the–art statistics–based local learners.
KeywordsFunction Approximation Locally Weighted Regression Input Space Structuring
Unable to display preview. Download preview PDF.
- 2.Finch, T.: Incremental calculation of weighted mean and variance. University of Cambridge (2009)Google Scholar
- 4.Nguyen-tuong, D., Peters, J.: Local gaussian process regression for real-time model-based robot control. In: Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2008, pp. 380–385 (2008)Google Scholar
- 5.Ritter, H., Martinetz, T., Schulten, K.: Neural computation and self-organizing maps - an introduction. Computation and neural systems series. Addison-Wesley (1992)Google Scholar
- 8.Stalph, P.O., Rubinsztajn, J., Sigaud, O., Butz, M.V.: A comparative study: function approximation with LWPR and XCSF. In: GECCO (Companion), pp. 1863–1870 (2010)Google Scholar