News for hackers. Stuff that matters.
Re:Hypernetworks: Neural Networks for Hierarchical Data by yobbo on Thursday February 05, 2026 @11:15PM (#46909046)
I think a latent embedding is almost equivalent to the article's hypernetwork, which I assume as y = (Wh + c)v + b, where h is a dataset-specific trainable vector. (The article uses multiple layers ...)

There are no comments on this comment yet.