The speaker says that learned features are similar across vision models despite differences in architecture, learning algorithm, and data details, suggesting that model structure depends on the problem’s structure rather than those choices.

“And it's regardless of the architecture and the particular learning algorithm and even the details of the data. And so the idea behind this is that the structure of your model does not really depend on the algorithm or on the data, but it, um, really depends on the structure of the problem that you're trying to learn.”