skada.TransferJointMatching
- skada.TransferJointMatching(base_estimator=None, n_components=None, tradeoff=0.01, kernel='rbf', max_iter=100, tol=0.01)[source]
- Parameters:
- base_estimatorobject, default=None
estimator used for fitting and prediction
- n_componentsint, default=None
The numbers of components to learn with PCA. Should be less or equal to the number of samples of the source and target data.
- tradeofffloat, default=1e-2
The tradeoff constant for the TJM algorithm. It serves to trade off feature matching and instance reweighting.
- max_iterint>0, default=100
The maximal number of iteration before stopping when fitting.
- kernelkernel object, default='rbf'
The kernel computed between data.
- tol
- Returns:
- pipelinePipeline
A pipeline containing a TransferJointMatchingAdapter.
References
[26][Long et al., 2014] Long, M., Wang, J., Ding, G., Sun, J., and Yu, P. (2014). Transfer joint matching for unsupervised domain adaptation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1410–1417
