Update README.md

README.md

@@ -1,8 +1,8 @@
 # Neural-Network-handwriting-recognition
 Single layey neural network, 40*40 pixels(1600 dimensions), 27 words dataset:
 1600 inputs---->27 neurons(using sigmoid)---->27outputs  
-Implemented base on https://github.com/timmmGZ/MachineLearning-Perceptron  
-# I haven't draw too much into the dataset, if the probabilty is less than 90% when you draw some word correctly, please add the drawing to train set, then train around 2000 times again.  
+Implemented base on https://github.com/timmmGZ/MachineLearning-Perceptron   
+I haven't draw too much into the dataset, if the probabilty is less than 90% when you draw some word correctly, please add the drawing to train set, then train around 2000 times again.  
 
 ![image](https://github.com/timmmGZ/Neural-Network-handwriting-recognition/blob/master/examplePictures/%E9%9B%B6.JPG)
 ![image](https://github.com/timmmGZ/Neural-Network-handwriting-recognition/blob/master/examplePictures/moon.JPG)
@@ -11,3 +11,5 @@ Implemented base on https://github.com/timmmGZ/MachineLearning-Perceptron
 ![image](https://github.com/timmmGZ/Neural-Network-handwriting-recognition/blob/master/examplePictures/car.JPG)
 ![image](https://github.com/timmmGZ/Neural-Network-handwriting-recognition/blob/master/examplePictures/apple.JPG)
 ![image](https://github.com/timmmGZ/Neural-Network-handwriting-recognition/blob/master/examplePictures/3.JPG)
+Here has a little bit update about generating random drawing:
+![image](https://github.com/timmmGZ/Neural-Network-handwriting-recognition/blob/master/examplePictures/randomDrawing(red).JPG)