A look at "liquid" neural nets, which change their underlying algorithms based on observed inputs, making them more flexible than standard ML neural networks (Steve Nadis/Quanta Magazine)

Steve Nadis / Quanta Magazine: A look at “liquid” neural nets, which change their underlying algorithms based on observed inputs, making them more flexible than standard ML neural networks  —  “Liquid” neural nets, based on a worm's nervous system, can transform their underlying algorithms on the fly, giving them unprecedented speed and adaptability.
http://www.techmeme.com/230212/p4?utm_source=dlvr.it&utm_medium=blogger#a230212p4