Re:An overview of the theory of overparameterized machine le...
by sdenton4 on Tuesday September 21, 2021 @03:37PM
(#28608960)
https://openreview.net/forum?id=Sy8gdB9xx
"our experiments establish that state-of-the-art convolutional networks for image classification trained with stochastic gradient methods easily fit a random labeling of the training data. This phenomenon is qualitatively unaffected by explicit regularization, and occurs even if we replace the true images by completely unstructured random noise."
It seems like the approach you describe just moves the complexity of the task solved by neural networks into the hashing function.