Week4 Machine Learning
รุ่นแก้ไขเมื่อ 03:26, 20 เมษายน 2550 โดย Parinya (คุย | มีส่วนร่วม) (→Properties of r.k. Hilbert spaces)
Let's first review some linear algebra concepts.
เนื้อหา
Hilbert spaces
Recall some basic definitions:
Def: An inner product is is a bilinear form on a pair of vectors satisfying
- and <v,v>
Note that every inner product space is a normed linear space with the norm
And with this norm, the inner product space forms a metric.
Def: A metric space is complete if every cauchy sequence converges to an element in the space
Def: A Hilbert space is a complete inner product space
Reproducing kernel Hilbert spaces
Let be a Hilbert space consisting of functions on . A function is called a reproducing kernel for if
- For all y, belongs to
- (Reproducing property): For all y, for all ,
Note that, in this case, dot-product is defined in a natural way, i.e.
Properties of r.k. Hilbert spaces
- It is known that if a r.k. exists for a given Hilbert space, then it is unique. The proof is two-line
- (Existence of K):
Eigenvector systems
Example 1: finite domain
We show a motivating example when is finite.