logoalt Hacker News

search_facility • today at 4:18 PM • 1 reply • view on HN

Nothing will happen, we already have kind of translation activities happen between "incompatible views" in real life, it works.

Besides, in weights there are no real incompatibility can happen, all is unified with same math chain through architecture. Different set of local minimums/maximums can have different strong/weak consequences but nothing incompatible.

Different consistent representations also mean that model probably can be simplier for the same task, sign of excessive capacity, imho

Replies

schiffern • today at 7:06 PM

  >Besides, in weights there are no real incompatibility can happen, all is unified with same math chain through architecture. Different set of local minimums/maximums can have different strong/weak consequences but nothing incompatible.
How do you know you're not stuck in a local minimum, always re-generating the God (or worse, the Demon) configuration and thinking it's universal?

This argument that incompatibility is impossible has an easy counterexample by looking at loss of coherence between two networks. You can still mash the weights together (so they're not "incompatible" in the basic number crunching, sure), but the resulting neural net is meaningless.

By "incompatible" I meant not in a software sense, but like two logical axiom systems can be incompatible.