Using gradient ascent to figure out how to change an input to be classified as a 5. (All images are the author’s own with all rights reserved).

Neural networks get a bad reputation for being black boxes. And while it certainly takes creativity to understand their decision making, they are really not as opaque as people would have you believe.

In this tutorial, I’ll show you how to use backpropagation to change the input as to classify it as whatever you would like.

Follow along using this colab.

(This work was co-written with Alfredo Canziani ahead of an upcoming video)

#2020 sep tutorials # overviews #neural networks #python #pytorch