Re:Neural Databases
by woadwarrior01 on Saturday October 17, 2020 @08:01AM
(#24809355)
The OP probably has something more in mind, but I'd imagine overfitting a small NN on a large dataset to a point of convergence and then shipping the small NN instead of the large dataset.
Re:Neural Databases
by throwaway9980 on Saturday October 17, 2020 @12:32PM
(#24811143)
Sounds like lossy (acceptable) compression.
Either way, I'm struggling to understand how it might work. Care to say more?