Decision Models vs. ML Classification

About 13 years ago I made https://jeena.net/catdog using machine learning algorithms to classify pictures of faces of dogs and cats and decide if we’re looking at a cat or a dog. I was in university and this was what I came up with doing for one of the assignments in the ML course.

Another guy came up with a evolutionary way to find math formulas which would over time be able to get closer and closer to a specific shape of a graph by doing copies and introducing random mutations to them, it was also very fascinating.

Anyway, now that Jev came out the decision models are all the rage right now but 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?

1 points | by jeena 1 hour ago

1 comments

  • amacalac 1 hour ago
    As far as I understand it; Jev et al can be considered Zero Shot Classifiers.

    It’s likely the system you built was trained on images of just cats and dogs; but Jev is using a general training set, and there is tuned for general purpose zero shot classification, rather than domain specific “is this a cat or a dog”.

    [-]
    • Iolaum 1 hour ago
      Another difference from me is the arbitary input. Classic ML models work on a predefined input. Jev-like models don't have that limitation. For example you can replace some columns if you get new info and the model will still work.