update

Author: mhjensen

doc/pub/week13/html/week13-bs.html

@@ -559,7 +559,7 @@ <h2 id="kullback-leibler-divergence" class="anchor">Kullback-Leibler divergence
 D_{KL}(p \| q) = \int_x p(x) \log \frac{p(x)}{q(x)} dx.
 $$
 
-<p>The KL-divegrnece \( D_{KL} \) achieves the minimum zero when \( p(x) == q(x) \) everywhere.</p>
+<p>The KL-divergence \( D_{KL} \) achieves the minimum zero when \( p(x) == q(x) \) everywhere.</p>
 
 <p>Note that the KL divergence is asymmetric. In cases where \( p(x) \) is
 close to zero, but \( q(x) \) is significantly non-zero, the \( q \)'s effect
@@ -579,7 +579,7 @@ <h2 id="jensen-shannon-divergence" class="anchor">Jensen-Shannon divergence </h2
 D_{JS}(p \| q) = \frac{1}{2} D_{KL}(p \| \frac{p + q}{2}) + \frac{1}{2} D_{KL}(q \| \frac{p + q}{2})
 $$
 
-<p>Many practitioners believe that one reason behind GANs' big success is
+<p>Many practitioners believe that one reason behind GANs' big success (to be discussed later) is
 switching the loss function from asymmetric KL-divergence in
 traditional maximum-likelihood approach to symmetric JS-divergence.
 </p>

doc/pub/week13/html/week13-reveal.html

@@ -485,7 +485,7 @@ <h2 id="kullback-leibler-divergence">Kullback-Leibler divergence </h2>
 $$
 <p>&nbsp;<br>
 
-<p>The KL-divegrnece \( D_{KL} \) achieves the minimum zero when \( p(x) == q(x) \) everywhere.</p>
+<p>The KL-divergence \( D_{KL} \) achieves the minimum zero when \( p(x) == q(x) \) everywhere.</p>
 
 <p>Note that the KL divergence is asymmetric. In cases where \( p(x) \) is
 close to zero, but \( q(x) \) is significantly non-zero, the \( q \)'s effect
@@ -508,7 +508,7 @@ <h2 id="jensen-shannon-divergence">Jensen-Shannon divergence </h2>
 $$
 <p>&nbsp;<br>
 
-<p>Many practitioners believe that one reason behind GANs' big success is
+<p>Many practitioners believe that one reason behind GANs' big success (to be discussed later) is
 switching the loss function from asymmetric KL-divergence in
 traditional maximum-likelihood approach to symmetric JS-divergence.
 </p>

doc/pub/week13/html/week13-solarized.html

@@ -490,7 +490,7 @@ <h2 id="kullback-leibler-divergence">Kullback-Leibler divergence </h2>
 D_{KL}(p \| q) = \int_x p(x) \log \frac{p(x)}{q(x)} dx.
 $$
 
-<p>The KL-divegrnece \( D_{KL} \) achieves the minimum zero when \( p(x) == q(x) \) everywhere.</p>
+<p>The KL-divergence \( D_{KL} \) achieves the minimum zero when \( p(x) == q(x) \) everywhere.</p>
 
 <p>Note that the KL divergence is asymmetric. In cases where \( p(x) \) is
 close to zero, but \( q(x) \) is significantly non-zero, the \( q \)'s effect
@@ -510,7 +510,7 @@ <h2 id="jensen-shannon-divergence">Jensen-Shannon divergence </h2>
 D_{JS}(p \| q) = \frac{1}{2} D_{KL}(p \| \frac{p + q}{2}) + \frac{1}{2} D_{KL}(q \| \frac{p + q}{2})
 $$
 
-<p>Many practitioners believe that one reason behind GANs' big success is
+<p>Many practitioners believe that one reason behind GANs' big success (to be discussed later) is
 switching the loss function from asymmetric KL-divergence in
 traditional maximum-likelihood approach to symmetric JS-divergence.
 </p>

doc/pub/week13/html/week13.html

@@ -567,7 +567,7 @@ <h2 id="kullback-leibler-divergence">Kullback-Leibler divergence </h2>
 D_{KL}(p \| q) = \int_x p(x) \log \frac{p(x)}{q(x)} dx.
 $$
 
-<p>The KL-divegrnece \( D_{KL} \) achieves the minimum zero when \( p(x) == q(x) \) everywhere.</p>
+<p>The KL-divergence \( D_{KL} \) achieves the minimum zero when \( p(x) == q(x) \) everywhere.</p>
 
 <p>Note that the KL divergence is asymmetric. In cases where \( p(x) \) is
 close to zero, but \( q(x) \) is significantly non-zero, the \( q \)'s effect
@@ -587,7 +587,7 @@ <h2 id="jensen-shannon-divergence">Jensen-Shannon divergence </h2>
 D_{JS}(p \| q) = \frac{1}{2} D_{KL}(p \| \frac{p + q}{2}) + \frac{1}{2} D_{KL}(q \| \frac{p + q}{2})
 $$
 
-<p>Many practitioners believe that one reason behind GANs' big success is
+<p>Many practitioners believe that one reason behind GANs' big success (to be discussed later) is
 switching the loss function from asymmetric KL-divergence in
 traditional maximum-likelihood approach to symmetric JS-divergence.
 </p>