typo

doc/pub/week39/html/week39-reveal.html

@@ -1809,8 +1809,7 @@ training data can have on order of millions of examples. Hence, it
 seems wasteful to compute the full cost function over the entire
 training set in order to perform only a single parameter update. A
 very common approach to addressing this challenge is to compute the
-gradient over batches of the training data. For example, in current
-a typical batch could contain some thousand  examples from
+gradient over batches of the training data. For example, a typical batch could contain some thousand  examples from
 an  entire training set of several millions. This batch is then used to
 perform a parameter update.
 </p>

doc/pub/week39/html/week39-solarized.html

@@ -1774,8 +1774,7 @@ training data can have on order of millions of examples. Hence, it
 seems wasteful to compute the full cost function over the entire
 training set in order to perform only a single parameter update. A
 very common approach to addressing this challenge is to compute the
-gradient over batches of the training data. For example, in current
-a typical batch could contain some thousand  examples from
+gradient over batches of the training data. For example, a typical batch could contain some thousand  examples from
 an  entire training set of several millions. This batch is then used to
 perform a parameter update.
 </p>

doc/pub/week39/html/week39.html

@@ -1851,8 +1851,7 @@ training data can have on order of millions of examples. Hence, it
 seems wasteful to compute the full cost function over the entire
 training set in order to perform only a single parameter update. A
 very common approach to addressing this challenge is to compute the
-gradient over batches of the training data. For example, in current
-a typical batch could contain some thousand  examples from
+gradient over batches of the training data. For example, a typical batch could contain some thousand  examples from
 an  entire training set of several millions. This batch is then used to
 perform a parameter update.
 </p>

doc/src/week39/week39.do.txt

@@ -1217,8 +1217,7 @@ training data can have on order of millions of examples. Hence, it
 seems wasteful to compute the full cost function over the entire
 training set in order to perform only a single parameter update. A
 very common approach to addressing this challenge is to compute the
-gradient over batches of the training data. For example, in current
-a typical batch could contain some thousand  examples from
+gradient over batches of the training data. For example, a typical batch could contain some thousand  examples from
 an  entire training set of several millions. This batch is then used to
 perform a parameter update.