--- a/writeup/aistats2011_cameraready.tex	Sat Mar 19 23:07:03 2011 -0400
+++ b/writeup/aistats2011_cameraready.tex	Sat Mar 19 23:11:17 2011 -0400
@@ -435,14 +435,8 @@
 \[
 P({\rm class}|{\rm input}=x)={\rm softmax}(b_2+W_2\tanh(b_1+W_1 x)),
 \] 
-i.e., two layers, where 
-\[
- p={\rm softmax}(a)
-\]
-means that 
-\[
- p_i(x)=\exp(a_i)/\sum_j \exp(a_j)
-\] 
+i.e., two layers, where $p={\rm softmax}(a)$ means that 
+$p_i(x)=\exp(a_i)/\sum_j \exp(a_j)$
 representing the probability 
 for class $i$, $\tanh$ is the element-wise
 hyperbolic tangent, $b_i$ are parameter vectors, and $W_i$ are