Here is a video of where my project is at,
Basically, it provides a graphical visualization of the network weights. I am going to experiment with generating and examining this sort of image through training. In this video, the network is training on six problems, and it slowly learns for about 45 seconds. After that, its learning skyrockets for brief amount of seconds. What if I had decided to stop training before 45 seconds? Seems problematic.
You can see in this image, the network is 11 pixels high, input and output rows and then 9 hidden layers. There are obvious horizontal and vertical lines and some occuring types of shapes, and lots of movement. The width of the hidden layers in the network are 100 pixels. The total image of the network is 11×100 pixels, and the network itself is 3x9x10x3 in shape.