Re:Decision Models vs. ML Classification
by amacalac on Sunday October 04, 2026 @01:40AM
(#49951004)
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”.
Re:Decision Models vs. ML Classification
by Iolaum on Sunday October 04, 2026 @02:13AM
(#49951148)
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.
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”.