Quantized variational autoencoders use discrete codes embedded in continuous manifolds, but this does not fundamentally change deep learning's nature—it still requires the discrete symbols to have continuous structure; if they do not (like prime numbers with no continuous structure), this approach fails completely because the artificial embedding cannot be used for meaningful interpolation.
factualpending
Speaker
François CholletEvidence Quote
“using discrete codes uh in a deep learning model does not fundamentally change the nature of deep learning.”
Source
Francois Chollet | Why abstraction is the key to intelligence, and what we’re still missing— Harvard CMSACreated: 8/12/2026, 6:07:58 PM
My Notes
Loading notes...