AI Dynamics

Global AI News Aggregator

Optimal Structure in End-to-End Learning: When to Remove Inductive Bias

Although the bitter lesson suggests that end-to-end eventually wins, this talk observes that at a given level of (compute, data, algorithm, architecture), there exists an optimal structure to add to make things work at all. But we often forget to remove these when more end-to-end

→ View original post on X — @_jasonwei,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *