ELBOW ROOM

This is where I collect and write things, mostly on academe and artificial intelligence. Established in 2010, by Vaishak Belle.

  1. image

    I find these two slides quickly gets the idea of our multiplexnet (AAAI, Hoernle eg al) across. We want to build neural networks that respect logical constraints, and satisfy these categorically. Ensuring that the sampling distribution stays within the bounding box, for instance, is an example of such a constraint.

    Jan. 18, 2023