AI Dynamics

Global AI News Aggregator

Neural Networks Still Fail at Basic Tasks Despite Progress

In 1969, Minsky & Papert showed that two-layered neural nets couldn’t learn to determine whether a figure was connected or not. Fast forward to 2024, with vastly more data, layers & compute, and neural nets (as we now know how to make them) still fail at some really basic stuff:

→ View original post on X — @garymarcus,

Commentaires

Leave a Reply

Your email address will not be published.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