5,322
edits
Unsupervised Learning: Difference between revisions
→Optimization
(Created page with "Basics of Unsupervised Learning ==Clustering== Given points <math>\{x^{(1)},...,x^{(m)}\}</math> we wish to group them into clusters 1,...,k.<br> Usually we are given the num...") |
|||
| Line 26: | Line 26: | ||
&= \sum_{j=1}{k} \sum_{i\mid z(i)=j} \nabla \Vert x^{(i)} - \mu_{j} \Vert ^2\\ | &= \sum_{j=1}{k} \sum_{i\mid z(i)=j} \nabla \Vert x^{(i)} - \mu_{j} \Vert ^2\\ | ||
&= \sum_{j=1}{k} \sum_{i\mid z(i)=j} 2(x^{(i)} - \mu_{j})\\ | &= \sum_{j=1}{k} \sum_{i\mid z(i)=j} 2(x^{(i)} - \mu_{j})\\ | ||
\implies \mu_{j} &= (\sum_{i\mid z(i)=j} x^(i))/(\sum_{i\mid z(i)=j} 1) | \implies \mu_{j} &= (\sum_{i\mid z(i)=j} x^(i))/(\sum_{i\mid z(i)=j} 1) \quad \forall j | ||
\end{align} | \end{align} | ||
</math> | </math> | ||
====Algorithm==== | ====Algorithm==== | ||