Alright thanks for the clarification. > So my question: Is there any other way to tackle the problem like "Transfer > Learning", "Zero-shot learning"? Any experience doing such task?
We don't have turn-key tools in scikit-learn for transfer learning nor zero-shot learning. It would be interesting to evaluate the impact of the covariate shift correction by computing of the impact of using shift corrected negative samples from trainingset A to train the model with samples with A and B together and evaluate only on a test set from B. -- Olivier ------------------------------------------------------------------------------ Get 100% visibility into Java/.NET code with AppDynamics Lite! It's a free troubleshooting tool designed for production. Get down to code-level detail for bottlenecks, with <2% overhead. Download for free and get started troubleshooting in minutes. http://pubads.g.doubleclick.net/gampad/clk?id=48897031&iu=/4140/ostg.clktrk _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
