From 9949fe98840cbf401b8c5213351d2894fe7872a3 Mon Sep 17 00:00:00 2001
From: Nimeas <lukas.martak@centrum.sk>
Date: Mon, 12 Mar 2018 21:32:32 +0100
Subject: [PATCH] Add missing word

---
 public/index.html | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/public/index.html b/public/index.html
index e541f1e..adde43b 100644
--- a/public/index.html
+++ b/public/index.html
@@ -414,7 +414,7 @@ <h2>Better Upsampling</h2>
   </figure>
 
   <p>Both deconvolution and the different resize-convolution approaches are linear operations, and can be interpreted as matrices.
-  This a helpful way to see the differences between them.
+  This is a helpful way to see the differences between them.
   Where deconvolution has a unique entry for each output window, resize-convolution is implicitly weight-tying in a way that discourages high frequency artifacts.</p>
 
   <p>We've had our best results with nearest-neighbor interpolation, and had difficulty making bilinear resize work.