Create an artificial neural network program (don't mistake for a perceptron) to recognize a 2 x 2 block to decide if it is "bright" or "dark". It needs 16 samples for training inputs (which can be anything; [1,1,1,1] for "bright", for example). It can be written in C++, Java, or Python. If in Python, please take a screenshot so I can apply appropriate indentation. Thank you!

To be classified as "bright", it must have 2, 3, or 4 white pixels. For "dark", it must be 0 or 1 white pixels.