Merge pull request #1 from MKAbdElrahman/master

Update ml.jmd
mitmath · Jan 13, 2020 · 070476a · 070476a
2 parents 3bc5f9e + c170485
commit 070476a
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/lecture2/ml.jmd b/lecture2/ml.jmd
@@ -119,7 +119,7 @@ computing. Let's showcase how to do some linear algebra by defining a neural
 network. Recall that a neural network is a function:
 
 ```math
-\text{NN}(x) = W_3\sigma_2(W_2\sigma_1(W_1x + b_1) + b2) + W_3
+\text{NN}(x) = W_3\sigma_2(W_2\sigma_1(W_1x + b_1) + b2) + b_3
 ```
 
 where we can change the number of layers (`(W_i,b_i)`) as necesary. Let's assume
@@ -422,7 +422,7 @@ NNODE(1.0)
 ```
 
 Instead of directly approximating the neural network, we will use the transformed
-equation that is forced to satisfy the boundary conditions. Using `u0=0.0`, we
+equation that is forced to satisfy the boundary conditions. Using `u0=1.0`, we
 have the function:
 
 ```julia