About 13 years ago I made https://jeena.net/catdog using machine learning algorithms to classify pictures to decide if we’re looking at a cat or a dog. Now that Jev came out the decision models are all the rage. I’m struggling to quite understand how different they are from what I did as a student in 2013. Is the big difference that I don’t need to manually choose the features to extract and do the preperation of the raw images? Or is there really something fundamentally new to their approach?