This is a cool exercise! After completing it, I wanted to find out exactly what each NN hidden node represented. I trained a tiny (10 hidden node) NN on an OCR dataset and created a visualization here: https://rawgithub.com/tashmore/nn-visualizer/master/nn_visua... .
Can anyone figure out what each hidden node represents?
You can also select a node and press "A" (Gradient Ascent). This will change the input in a way that increases the selected node's value. By selecting an output node and mashing "A", you can run the NN in reverse, causing it to "hallucinate" a digit.
Can anyone figure out what each hidden node represents?
You can also select a node and press "A" (Gradient Ascent). This will change the input in a way that increases the selected node's value. By selecting an output node and mashing "A", you can run the NN in reverse, causing it to "hallucinate" a digit.