I don't really understand the folowing graphic wich illustrate One vs All: http://scikit-learn.org/dev/auto_examples/linear_model/plot_sgd_iris.html#sphx-glr-auto-examples-linear-model-plot-sgd-iris-py

The score function computed in SGD classifier is the signed distance from the decision line (dashed one). Due to one vs all strategy i was expecting that the plain delimitation of prediction between red and blue would be the bissectrice of the angle formed by the blue and red dashed lines. That is not the case, why ?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.