The natural latents machinery says a lot about what information needs to be passed around, but says a lot less about how to represent it. What representations are natural?
I like this question. The direction I’m currently thinking is spaces and distributions within them.
What we’d ideally like is to figure out how environment structure gets represented in the net, without needing to know what environment structure gets represented in the net (or even what structure is in the environment in the first place). That way, we can look inside trained nets to figure out what structure is in the environment.
If we consider that inputs and outputs of nets contain distributions which are implied at training time, the net may be storing transformations that do not capture or represent any given aspect of the distribution it operates on, specifically in cases where details of the distribution are irrelevant to the operation it performs. However, this means I am optimistic about unsupervised methods, eg, autoencoders and sequence predictors.
I like this question. The direction I’m currently thinking is spaces and distributions within them.
If we consider that inputs and outputs of nets contain distributions which are implied at training time, the net may be storing transformations that do not capture or represent any given aspect of the distribution it operates on, specifically in cases where details of the distribution are irrelevant to the operation it performs. However, this means I am optimistic about unsupervised methods, eg, autoencoders and sequence predictors.