fix image

Author: Alvant

README.md

@@ -28,11 +28,11 @@ Consider using TopicNet if:
     <em>
         Example of the two-stage experiment scheme.
         At the first stage, regularizer with parameter <img src="https://render.githubusercontent.com/render/math?math=\tau"> taking values in some range <img src="https://render.githubusercontent.com/render/math?math=\{\tau_1, \tau_2, \tau_3\}"> is applied.
-        Best models after the first stage are <em>Model 1</em> and <em>Model 2</em>~---~so <em>Model 3</em> is not taking part in the training process anymore.
+        Best models after the first stage are <em>Model 1</em> and <em>Model 2</em> — so <em>Model 3</em> is not taking part in the training process anymore.
         The second stage is connected with another regularizer with parameter <img src="https://render.githubusercontent.com/render/math?math=\xi"> taking values in range <img src="https://render.githubusercontent.com/render/math?math=\{\xi_1, \xi_2\}">.
         As a result of this stage, two descendant models of <em>Model 1</em> and two descendant models of <em>Model 2</em> are obtained.
     </em>
-</div>div>
+</div>
 
 
 [![GitHub contributors](https://img.shields.io/github/contributors/machine-intelligence-laboratory/TopicNet)](https://github.com/machine-intelligence-laboratory/TopicNet/graphs/contributors)