diff --git a/blog/a_violent_introduction_to_linear_regression.html b/blog/a_violent_introduction_to_linear_regression.html
index d745f19..50941dc 100644
--- a/blog/a_violent_introduction_to_linear_regression.html
+++ b/blog/a_violent_introduction_to_linear_regression.html
@@ -58,7 +58,7 @@ <h2>
 
             <p> now onto gradient descent! </p>
 
-            <p class="whisper"> the below is a general explanation of gradient descent. there are many variations of gradient descent depending on the size of the sample used in backpropagation, we foxus here on stochastic gradient descent. </p>
+            <p class="whisper"> the below is a general explanation of gradient descent. there are many variations of gradient descent depending on the size of the sample used in backpropagation, we focus here on stochastic gradient descent. </p>
 
             <p> the best way to think about gradient descent is in the shoes of an adventurer navigating some vast, hilly terrain looking for the point with lowest altitude. your current location will have a certain steepness in each direction that you can walk in. to find the point with the lowest altitude, as fast as possible, you'd want to walk off the steepest cliff you can find. </p>