Back to Search
Start Over
A fully Bayesian approach to kernel-based regularization for impulse response estimation⁎
- Publication Year :
- 2018
-
Abstract
- Kernel-based regularization has recently been shown to be a successful method for impulse response estimation. This technique usually requires choosing a vector of hyper-parameters in order to form an appropriate regularization matrix. In this paper, we develop an alternative way to obtain kernel-based regularization estimates by Bayesian model mixing. This new approach is tested against state-of-the-art methods for hyperparameter tuning in regularized FIR estimation, with favorable results in many cases.
Details
- Database :
- OAIster
- Notes :
- González, Rodrigo A., Rojas, Cristian R.
- Publication Type :
- Electronic Resource
- Accession number :
- edsoai.on1235041936
- Document Type :
- Electronic Resource
- Full Text :
- https://doi.org/10.1016.j.ifacol.2018.09.123