The idea of support vector machine (SVM) is to maximize the distance of the separating
plane to the closest observation which are referred as the support vectors. Let g(x)=
w_(0)+w_(1)x_(1)+w_(2)x_(2)=0 be the separating line. For a given sample x=(x_(1),x_(2)), the distance
of x to the straight line g(x)=0, is
(|w_(0)+w_(1)x_(1)+w_(2)x_(2)|)/(sqrt(w_(1)^(2)+w_(2)^(2))).
Let the separating line be x_(1)+2x_(2)-3=0, and the given observation is x=(1.5,1.5).
Calculate the distance of the observation to the separating line.
(|w_(0)+w_(1)x_(1)+w_(2)x_(2)|)/(sqrt(w_(1)^(2)+w_(2)^(2)))=(|1.5+2**1.5-3|)/(sqrt(1^(2)+2^(2)))=0.6708204.
In the linear SVM, the dot product x_(i)^(T)x_(j) is an important operation which facilitates
the calculation of the Euclidean distance. Let the nonlinear mapping of the sam-
ple from the original space to the projected space be phi . In nonlinear SVM, the dot
product between the images of the mapping phi (x_(i)) and phi (x_(j)) are calculated by the ker-
nel function K(x_(i),x_(j))=phi (x_(i))^(T)phi (x_(j)). Suppose in the original space x_(i)=(x_(i1),x_(i2))
and x_(j)=(x_(j1),x_(j2)). The nonlinear mappings are phi (x_(i))=(x_(i1)^(2),x_(i2)^(2),sqrt(2)x_(i1)x_(i2)) and
phi (x_(j))=(x_(j1)^(2),x_(j2)^(2),sqrt(2)x_(j1)x_(j2)). Calculate the kernel function K(x_(i),x_(j)). If it is a poly-
nomial kernel function, determine the degrees of the polynomial kernel function.
The idea of support vector machine (SVM) is to maximize the distance of the separating plane to the closest observation which are referred as the support vectors. Let g() = + 1 + 2 = 0 be the separating line. For a given sample = (1,), the distance of to the straight line g() = 0, is [wo + W1X1 + W2X2| w+w2
4
Let the separating line be 1 +2x2 -3 = 0, and the given observation is = (1.5,1.5) Calculate the distance of the observation to the separating line.
Vw+wz
/12 + 22
In the linear SVM, the dot product Tx, is an important operation which facilitates the calculation of the Euclidean distance. Let the nonlinear mapping of the sam ple from the original space to the projected space be . In nonlinear SVM, the dot product between the images of the mapping (,) and (,) are calculated by the ker- nel function Kx,) =(x)T(x). Suppose in the original space _= (x,2)
(x)= (x1.322x12.Calculate the kernel function K(,,x).If it is a poly- nomial kernel function, determine the degrees of the polynomial kernel function.