Using the MNIST database of handwritten digits MNIST database – Wikipedia a convolutional neural network was trained to an accuracy of 90%. This took 50 epochs.
![](http://sound-analysis.com/wp-content/uploads/2023/04/image-1024x649.png)
The trained model was loaded into the Image Classifier control and used to identify handwritten digits.
![](http://sound-analysis.com/wp-content/uploads/2023/04/image-2-1024x450.png)
The files required to reproduce this demo are available here https://drive.google.com/file/d/1XKSYvJfAW1maNsaiV0iaWZXor0Tbtuat/view?usp=share_link