ผลต่างระหว่างรุ่นของ "Week4 Machine Learning"

จาก Theory Wiki
ไปยังการนำทาง ไปยังการค้นหา
 
(ไม่แสดง 1 รุ่นระหว่างกลางโดยผู้ใช้คนเดียวกัน)
แถว 25: แถว 25:
 
Note that, in this case, dot-product is defined in a natural way, i.e.  
 
Note that, in this case, dot-product is defined in a natural way, i.e.  
 
:<math> <f,g> = \int_{X} f(x) \bar{g}(x) </math>
 
:<math> <f,g> = \int_{X} f(x) \bar{g}(x) </math>
 +
 +
== 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 <math>\mathcal{X}</math> is finite.

รุ่นแก้ไขปัจจุบันเมื่อ 03:26, 20 เมษายน 2550

Let's first review some linear algebra concepts.

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.