Trying to make my own version of the "quick draw" game to build a library and teach an AI as a BEGINNER

[paulgoux]

I stumbled upon a great little example for neual networks a while back in processing.

Improving the accuracy of a neural network for digit recognition

I’m attempting to code a neural network to recognise handwritten characters currently using the mnist digit database. I’m specifically using a lower 14x14 resolution. I created a new neural network which is initialised with the number of inputs necessary the number of hidden layers and the number of outputs. Then I train it based on the dataset using an 80/20 test train split. The sigmoid function is calculated before hand and an array of 200 is used to store values which I can then lookup. Th…

Its a simple network allows you to specify how deep you would like the network. It only makes use of the signoid function. And the sigmoid is calculated in setup to save computation time.

Do bear in mind that there are no filters or encoders its just the network and the neurons.