diff --git a/tutorial_deep_learning_basics/deep_learning_basics.ipynb b/tutorial_deep_learning_basics/deep_learning_basics.ipynb
index 2b4f48f..2bbb40a 100644
--- a/tutorial_deep_learning_basics/deep_learning_basics.ipynb
+++ b/tutorial_deep_learning_basics/deep_learning_basics.ipynb
@@ -46,7 +46,7 @@
     "\n",
     "![Deep learning concepts](https://i.imgur.com/EAl47rp.png)\n",
     "\n",
-    "At a high-level, neural networks are either encoders, decoders, or a combination of both. Encoders find patterns in raw data to form compact, useful representations. Decoders generate new data or high-resolution useful infomation from those representations. As the lecture describes, deep learning discovers ways to **represent** the world so that we can reason about it. The rest is clever methods that help use deal effectively with visual information, language, sound (#1-6) and even act in a world based on this information and occasional rewards (#7).\n",
+    "At a high-level, neural networks are either encoders, decoders, or a combination of both. Encoders find patterns in raw data to form compact, useful representations. Decoders generate new data or high-resolution useful infomation from those representations. As the lecture describes, deep learning discovers ways to **represent** the world so that we can reason about it. The rest is clever methods that help us deal effectively with visual information, language, sound (#1-6) and even act in a world based on this information and occasional rewards (#7).\n",
     "\n",
     "1. **Feed Forward Neural Networks (FFNNs)** - classification and regression based on features. See [Part 1](#Part-1:-Boston-Housing-Price-Prediction-with-Feed-Forward-Neural-Networks) of this tutorial for an example.\n",
     "2. **Convolutional Neural Networks (CNNs)** - image classification, object detection, video action recognition, etc. See [Part 2](#Part-2:-Classification-of-MNIST-Dreams-with-Convolution-Neural-Networks) of this tutorial for an example.\n",