Update README.md

README.md

@@ -19,17 +19,19 @@ Anti-aliased residual CNN for CIFAR-10 image classification, designed to improve
 
 ## Problem
 
-Downsampling operations are linear maps from a high-dimensional space to a lower-dimensional one. 
+### NULA 
 
+Anti-aliased residual CNN for CIFAR-10 image classification, designed to improve robustness against perturbations that exploit downsampling.
+
+### Problem
+
+Downsampling operations are linear maps from a high-dimensional space to a lower-dimensional one.
 
 $D : \mathbb{R}^n \to \mathbb{R}^m, \quad \text{where } n > m$
+
 $\dim(\ker(D)) = n - \text{rank}(D)$
 
-  
-By the Rank-Nullity thereom, this matrix has a massive NULL space. An attacker can exploit this.
-They can use the discarded samples of these downsampling operations as extra degrees of freedom.
-By sculpting perturbations with components in the null space of the downsampling operator, 
-they spread energy across frequencies that are discarded during striding
+By the Rank-Nullity theorem, this matrix has a massive NULL space. An attacker can exploit this. They can use the discarded samples of these downsampling operations as extra degrees of freedom. By sculpting perturbations with components in the null space of the downsampling operator, they spread energy across frequencies that are discarded during striding.
 
 The result is an image perceptually identical to the original, with a manipulated activation pattern.