foreword
Recently, I have been reading and sorting out the content of support vector machines, and read many excellent blog posts. The main reference is this senior's popular introduction to support vector machines (understanding the three-level realm of SVM) . The following are some of my thoughts and notes during the reading process.
1. Understand SVM
So the objective function becomes max γ ^ = max 1 ∣ ∣ w ∣ ∣ s . t . , yi ( w T xi + b ) ≥ 1 , i = 1 , . . . , n max\ \widehat \gamma=max\ frac{1}{||w||}\qquad st,\ \ y_i(w^Tx_i+b)\ge1,\ i=1,...,nmax c
=max∣∣w∣∣1s.t., yi(wTxi+b)≥1, i=1,...,n