GMM w_i typo

ppwwyyxx · Jan 3, 2014 · 09b88b9 · 09b88b9
1 parent 86a239f
commit 09b88b9
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/doc/Final-Report-Complete/model.tex b/doc/Final-Report-Complete/model.tex
@@ -15,7 +15,7 @@ \subsection{GMM}
 \[\mathcal{N}(x | \mathbf{\mu}_i, \Sigma_i) = \dfrac{1}{(2\pi)^{\frac{d}{2}}\sqrt{|\Sigma_i|}}
 \exp \left({-\dfrac{1}{2}(x-\mu_i)^T\Sigma_i^{-1}(x-\mu_i)}\right)\]
 subject to
-\[\sum_{i=1}^{K} w_i = 0\]
+\[\sum_{i=1}^{K} w_i = 1\]
 
   Therefore, GMM is merely a weighted combination of multivariate Gaussian distribution which
   assumes feature vectors are independent.