typo

README.md

@@ -13,4 +13,4 @@ A super tiny mnist model to demostrate the potential of the learnable activation
 The model can reach 96.6% accuracy with only a 1.3k parameter-size.
 
 The OptAEG-V1 learnable activation is based on a theory of Arithmetic Expression Geometry which is still in developing.
-Please visit the draft papers on [theory](https://github.com/mountain/aeg-paper) and [neurual networks](https://github.com/mountain/optim-aeg) for a reference
+Please visit the draft papers on [theory](https://github.com/mountain/aeg-paper) and [neural networks](https://github.com/mountain/optim-aeg) for a reference