diff --git a/Using-TensorFlow-Lite-for-the-Ultimate-Goal-Challenge.md b/Using-TensorFlow-Lite-for-the-Ultimate-Goal-Challenge.md
index 5d70a94..11792e7 100644
--- a/Using-TensorFlow-Lite-for-the-Ultimate-Goal-Challenge.md
+++ b/Using-TensorFlow-Lite-for-the-Ultimate-Goal-Challenge.md
@@ -6,7 +6,7 @@
 For this season's challenge, the inference model was trained to recognize a single Ultimate Goal ring.  The model was also trained to recognize a stack of four rings.  This was done since it is easier to train a model to distinguish between a single and quadruple ring stack, rather than training a model that can reliably distinguish the individual rings of a multi-ring stack.
 
 ### How Might a Team Use TensorFlow in the Ultimate Goal Challenge?
-For this season's challenge, during the pre-Match stage a die is rolled and the field is randomized.  
+For this season's challenge, during the pre-Match stage a single die is rolled and the field is randomized.  
 
 <p align="center">[[/images/Blocks-Sample-TensorFlow-Object-Detection-Op-Mode/randomization.png]]<p>